Hugging Face's logo

Nhckdvrl
/
cvis-ablate

Transformers
Safetensors
c-vis
ablation
grpo
qwen3.5
Model card Files
xet
 Community
Nhckdvrl commited on
Commit
e5fb487
·
verified ·
1 Parent(s): 81f7e65

Add a4_fixed_images/round_3: MathVision 53.95%, MathVista 82.80%, MMMU 68.22% (part 2)

Browse files
Files changed (10) hide show
  1. .gitattributes +1 -0
  2. a4_fixed_images/round_3/model-00002-of-00004.safetensors +3 -0
  3. a4_fixed_images/round_3/model-00003-of-00004.safetensors +3 -0
  4. a4_fixed_images/round_3/model-00004-of-00004.safetensors +3 -0
  5. a4_fixed_images/round_3/model.safetensors.index.json +768 -0
  6. a4_fixed_images/round_3/preprocessor_config.json +21 -0
  7. a4_fixed_images/round_3/processor_config.json +60 -0
  8. a4_fixed_images/round_3/tokenizer.json +3 -0
  9. a4_fixed_images/round_3/tokenizer_config.json +33 -0
  10. a4_fixed_images/round_3/trainer_state.json +2454 -0
.gitattributes CHANGED
@@ -47,3 +47,4 @@ c4_no_difficulty_filter/round_1/tokenizer.json filter=lfs diff=lfs merge=lfs -te
47
  c4_no_difficulty_filter/round_2/tokenizer.json filter=lfs diff=lfs merge=lfs -text
48
  c4_no_difficulty_filter/round_3/tokenizer.json filter=lfs diff=lfs merge=lfs -text
49
  c4_no_difficulty_filter/round_4/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
47
  c4_no_difficulty_filter/round_2/tokenizer.json filter=lfs diff=lfs merge=lfs -text
48
  c4_no_difficulty_filter/round_3/tokenizer.json filter=lfs diff=lfs merge=lfs -text
49
  c4_no_difficulty_filter/round_4/tokenizer.json filter=lfs diff=lfs merge=lfs -text
50
+ a4_fixed_images/round_3/tokenizer.json filter=lfs diff=lfs merge=lfs -text
a4_fixed_images/round_3/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6594864f923a2ed170acd4c248163251595ad915fed5b9f3213c129cf3cc9421
3
+ size 4987757928
a4_fixed_images/round_3/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d275f6af1bbfcc20f5709cc952e10abbf45e0a11e0360257b212d94dfcfa6f3
3
+ size 4954810240
a4_fixed_images/round_3/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57c65b4941736a75cd7fff8a6ac2abb636f707e3a232955bd63e4f0861f13d41
3
+ size 3934446832
a4_fixed_images/round_3/model.safetensors.index.json ADDED
@@ -0,0 +1,768 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 1469680,
4
+ "total_size": 18819627488
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00001-of-00004.safetensors",
8
+ "model.language_model.embed_tokens.weight": "model-00001-of-00004.safetensors",
9
+ "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
10
+ "model.language_model.layers.0.linear_attn.A_log": "model-00001-of-00004.safetensors",
11
+ "model.language_model.layers.0.linear_attn.conv1d.weight": "model-00001-of-00004.safetensors",
12
+ "model.language_model.layers.0.linear_attn.dt_bias": "model-00001-of-00004.safetensors",
13
+ "model.language_model.layers.0.linear_attn.in_proj_a.weight": "model-00001-of-00004.safetensors",
14
+ "model.language_model.layers.0.linear_attn.in_proj_b.weight": "model-00001-of-00004.safetensors",
15
+ "model.language_model.layers.0.linear_attn.in_proj_qkv.weight": "model-00001-of-00004.safetensors",
16
+ "model.language_model.layers.0.linear_attn.in_proj_z.weight": "model-00001-of-00004.safetensors",
17
+ "model.language_model.layers.0.linear_attn.norm.weight": "model-00001-of-00004.safetensors",
18
+ "model.language_model.layers.0.linear_attn.out_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
22
+ "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
23
+ "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
24
+ "model.language_model.layers.1.linear_attn.A_log": "model-00001-of-00004.safetensors",
25
+ "model.language_model.layers.1.linear_attn.conv1d.weight": "model-00001-of-00004.safetensors",
26
+ "model.language_model.layers.1.linear_attn.dt_bias": "model-00001-of-00004.safetensors",
27
+ "model.language_model.layers.1.linear_attn.in_proj_a.weight": "model-00001-of-00004.safetensors",
28
+ "model.language_model.layers.1.linear_attn.in_proj_b.weight": "model-00001-of-00004.safetensors",
29
+ "model.language_model.layers.1.linear_attn.in_proj_qkv.weight": "model-00001-of-00004.safetensors",
30
+ "model.language_model.layers.1.linear_attn.in_proj_z.weight": "model-00001-of-00004.safetensors",
31
+ "model.language_model.layers.1.linear_attn.norm.weight": "model-00001-of-00004.safetensors",
32
+ "model.language_model.layers.1.linear_attn.out_proj.weight": "model-00001-of-00004.safetensors",
33
+ "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
34
+ "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
35
+ "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
36
+ "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
37
+ "model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
38
+ "model.language_model.layers.10.linear_attn.A_log": "model-00002-of-00004.safetensors",
39
+ "model.language_model.layers.10.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
40
+ "model.language_model.layers.10.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
41
+ "model.language_model.layers.10.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
42
+ "model.language_model.layers.10.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
43
+ "model.language_model.layers.10.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
44
+ "model.language_model.layers.10.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
45
+ "model.language_model.layers.10.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
46
+ "model.language_model.layers.10.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.language_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
49
+ "model.language_model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.language_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
51
+ "model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
52
+ "model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
54
+ "model.language_model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
56
+ "model.language_model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
57
+ "model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
58
+ "model.language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.language_model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
60
+ "model.language_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
63
+ "model.language_model.layers.12.linear_attn.A_log": "model-00002-of-00004.safetensors",
64
+ "model.language_model.layers.12.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
65
+ "model.language_model.layers.12.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
66
+ "model.language_model.layers.12.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
67
+ "model.language_model.layers.12.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
68
+ "model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
69
+ "model.language_model.layers.12.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
70
+ "model.language_model.layers.12.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
71
+ "model.language_model.layers.12.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
72
+ "model.language_model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
74
+ "model.language_model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
76
+ "model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
77
+ "model.language_model.layers.13.linear_attn.A_log": "model-00002-of-00004.safetensors",
78
+ "model.language_model.layers.13.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
79
+ "model.language_model.layers.13.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
80
+ "model.language_model.layers.13.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
81
+ "model.language_model.layers.13.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
82
+ "model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
83
+ "model.language_model.layers.13.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
84
+ "model.language_model.layers.13.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
85
+ "model.language_model.layers.13.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
86
+ "model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.language_model.layers.13.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
88
+ "model.language_model.layers.13.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
89
+ "model.language_model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
90
+ "model.language_model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors",
91
+ "model.language_model.layers.14.linear_attn.A_log": "model-00003-of-00004.safetensors",
92
+ "model.language_model.layers.14.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
93
+ "model.language_model.layers.14.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
94
+ "model.language_model.layers.14.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
95
+ "model.language_model.layers.14.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
96
+ "model.language_model.layers.14.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
97
+ "model.language_model.layers.14.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
98
+ "model.language_model.layers.14.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
99
+ "model.language_model.layers.14.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
100
+ "model.language_model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
101
+ "model.language_model.layers.14.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
102
+ "model.language_model.layers.14.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
103
+ "model.language_model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
104
+ "model.language_model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors",
105
+ "model.language_model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
106
+ "model.language_model.layers.15.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
107
+ "model.language_model.layers.15.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
108
+ "model.language_model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
109
+ "model.language_model.layers.15.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
110
+ "model.language_model.layers.15.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
111
+ "model.language_model.layers.15.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
112
+ "model.language_model.layers.15.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
113
+ "model.language_model.layers.15.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
114
+ "model.language_model.layers.15.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
115
+ "model.language_model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
116
+ "model.language_model.layers.16.linear_attn.A_log": "model-00003-of-00004.safetensors",
117
+ "model.language_model.layers.16.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
118
+ "model.language_model.layers.16.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
119
+ "model.language_model.layers.16.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
120
+ "model.language_model.layers.16.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
121
+ "model.language_model.layers.16.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
122
+ "model.language_model.layers.16.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
123
+ "model.language_model.layers.16.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
124
+ "model.language_model.layers.16.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
125
+ "model.language_model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
126
+ "model.language_model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
127
+ "model.language_model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
128
+ "model.language_model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
129
+ "model.language_model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
130
+ "model.language_model.layers.17.linear_attn.A_log": "model-00003-of-00004.safetensors",
131
+ "model.language_model.layers.17.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
132
+ "model.language_model.layers.17.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
133
+ "model.language_model.layers.17.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
134
+ "model.language_model.layers.17.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
135
+ "model.language_model.layers.17.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
136
+ "model.language_model.layers.17.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
137
+ "model.language_model.layers.17.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
138
+ "model.language_model.layers.17.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
139
+ "model.language_model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
140
+ "model.language_model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
141
+ "model.language_model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.language_model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
143
+ "model.language_model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
144
+ "model.language_model.layers.18.linear_attn.A_log": "model-00003-of-00004.safetensors",
145
+ "model.language_model.layers.18.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
146
+ "model.language_model.layers.18.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
147
+ "model.language_model.layers.18.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
148
+ "model.language_model.layers.18.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
149
+ "model.language_model.layers.18.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
150
+ "model.language_model.layers.18.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
151
+ "model.language_model.layers.18.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
152
+ "model.language_model.layers.18.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
153
+ "model.language_model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
154
+ "model.language_model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
155
+ "model.language_model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
156
+ "model.language_model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
157
+ "model.language_model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
158
+ "model.language_model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
159
+ "model.language_model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
160
+ "model.language_model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
161
+ "model.language_model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
162
+ "model.language_model.layers.19.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
163
+ "model.language_model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
164
+ "model.language_model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
165
+ "model.language_model.layers.19.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
166
+ "model.language_model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.language_model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
169
+ "model.language_model.layers.2.linear_attn.A_log": "model-00001-of-00004.safetensors",
170
+ "model.language_model.layers.2.linear_attn.conv1d.weight": "model-00001-of-00004.safetensors",
171
+ "model.language_model.layers.2.linear_attn.dt_bias": "model-00001-of-00004.safetensors",
172
+ "model.language_model.layers.2.linear_attn.in_proj_a.weight": "model-00001-of-00004.safetensors",
173
+ "model.language_model.layers.2.linear_attn.in_proj_b.weight": "model-00001-of-00004.safetensors",
174
+ "model.language_model.layers.2.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
175
+ "model.language_model.layers.2.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
176
+ "model.language_model.layers.2.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
177
+ "model.language_model.layers.2.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
178
+ "model.language_model.layers.2.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
179
+ "model.language_model.layers.2.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
180
+ "model.language_model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
181
+ "model.language_model.layers.2.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
182
+ "model.language_model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
183
+ "model.language_model.layers.20.linear_attn.A_log": "model-00003-of-00004.safetensors",
184
+ "model.language_model.layers.20.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
185
+ "model.language_model.layers.20.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
186
+ "model.language_model.layers.20.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
187
+ "model.language_model.layers.20.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
188
+ "model.language_model.layers.20.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
189
+ "model.language_model.layers.20.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
190
+ "model.language_model.layers.20.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
191
+ "model.language_model.layers.20.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.language_model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
193
+ "model.language_model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
194
+ "model.language_model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.language_model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
196
+ "model.language_model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
197
+ "model.language_model.layers.21.linear_attn.A_log": "model-00003-of-00004.safetensors",
198
+ "model.language_model.layers.21.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
199
+ "model.language_model.layers.21.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
200
+ "model.language_model.layers.21.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
201
+ "model.language_model.layers.21.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
202
+ "model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
203
+ "model.language_model.layers.21.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
204
+ "model.language_model.layers.21.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
205
+ "model.language_model.layers.21.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
206
+ "model.language_model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
207
+ "model.language_model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.language_model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.language_model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
210
+ "model.language_model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
211
+ "model.language_model.layers.22.linear_attn.A_log": "model-00003-of-00004.safetensors",
212
+ "model.language_model.layers.22.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
213
+ "model.language_model.layers.22.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
214
+ "model.language_model.layers.22.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
215
+ "model.language_model.layers.22.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
216
+ "model.language_model.layers.22.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
217
+ "model.language_model.layers.22.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
218
+ "model.language_model.layers.22.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
219
+ "model.language_model.layers.22.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
220
+ "model.language_model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
221
+ "model.language_model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
222
+ "model.language_model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
223
+ "model.language_model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
224
+ "model.language_model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
+ "model.language_model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.language_model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.language_model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.language_model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.language_model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
230
+ "model.language_model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.language_model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.language_model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
233
+ "model.language_model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
234
+ "model.language_model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
235
+ "model.language_model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
236
+ "model.language_model.layers.24.linear_attn.A_log": "model-00003-of-00004.safetensors",
237
+ "model.language_model.layers.24.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
238
+ "model.language_model.layers.24.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
239
+ "model.language_model.layers.24.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
240
+ "model.language_model.layers.24.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
241
+ "model.language_model.layers.24.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
242
+ "model.language_model.layers.24.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
243
+ "model.language_model.layers.24.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
244
+ "model.language_model.layers.24.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
245
+ "model.language_model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
246
+ "model.language_model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
247
+ "model.language_model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
248
+ "model.language_model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
249
+ "model.language_model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
250
+ "model.language_model.layers.25.linear_attn.A_log": "model-00003-of-00004.safetensors",
251
+ "model.language_model.layers.25.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
252
+ "model.language_model.layers.25.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
253
+ "model.language_model.layers.25.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
254
+ "model.language_model.layers.25.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
255
+ "model.language_model.layers.25.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
256
+ "model.language_model.layers.25.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
257
+ "model.language_model.layers.25.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
258
+ "model.language_model.layers.25.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
259
+ "model.language_model.layers.25.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
260
+ "model.language_model.layers.25.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
261
+ "model.language_model.layers.25.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
262
+ "model.language_model.layers.25.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
263
+ "model.language_model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
264
+ "model.language_model.layers.26.linear_attn.A_log": "model-00004-of-00004.safetensors",
265
+ "model.language_model.layers.26.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
266
+ "model.language_model.layers.26.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
267
+ "model.language_model.layers.26.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
268
+ "model.language_model.layers.26.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
269
+ "model.language_model.layers.26.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
270
+ "model.language_model.layers.26.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
271
+ "model.language_model.layers.26.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
272
+ "model.language_model.layers.26.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
273
+ "model.language_model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
274
+ "model.language_model.layers.26.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
275
+ "model.language_model.layers.26.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
276
+ "model.language_model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
277
+ "model.language_model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
278
+ "model.language_model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
279
+ "model.language_model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
280
+ "model.language_model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
281
+ "model.language_model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
282
+ "model.language_model.layers.27.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
283
+ "model.language_model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
284
+ "model.language_model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
285
+ "model.language_model.layers.27.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
286
+ "model.language_model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
287
+ "model.language_model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
288
+ "model.language_model.layers.28.input_layernorm.weight": "model-00004-of-00004.safetensors",
289
+ "model.language_model.layers.28.linear_attn.A_log": "model-00004-of-00004.safetensors",
290
+ "model.language_model.layers.28.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
291
+ "model.language_model.layers.28.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
292
+ "model.language_model.layers.28.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
293
+ "model.language_model.layers.28.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
294
+ "model.language_model.layers.28.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
295
+ "model.language_model.layers.28.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
296
+ "model.language_model.layers.28.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
297
+ "model.language_model.layers.28.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
298
+ "model.language_model.layers.28.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
299
+ "model.language_model.layers.28.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
300
+ "model.language_model.layers.28.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
301
+ "model.language_model.layers.28.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
302
+ "model.language_model.layers.29.input_layernorm.weight": "model-00004-of-00004.safetensors",
303
+ "model.language_model.layers.29.linear_attn.A_log": "model-00004-of-00004.safetensors",
304
+ "model.language_model.layers.29.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
305
+ "model.language_model.layers.29.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
306
+ "model.language_model.layers.29.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
307
+ "model.language_model.layers.29.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
308
+ "model.language_model.layers.29.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
309
+ "model.language_model.layers.29.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
310
+ "model.language_model.layers.29.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
311
+ "model.language_model.layers.29.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
312
+ "model.language_model.layers.29.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
313
+ "model.language_model.layers.29.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
314
+ "model.language_model.layers.29.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
315
+ "model.language_model.layers.29.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
316
+ "model.language_model.layers.3.input_layernorm.weight": "model-00002-of-00004.safetensors",
317
+ "model.language_model.layers.3.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
318
+ "model.language_model.layers.3.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
319
+ "model.language_model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
320
+ "model.language_model.layers.3.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
321
+ "model.language_model.layers.3.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
322
+ "model.language_model.layers.3.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
323
+ "model.language_model.layers.3.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
324
+ "model.language_model.layers.3.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
325
+ "model.language_model.layers.3.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
326
+ "model.language_model.layers.3.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
327
+ "model.language_model.layers.30.input_layernorm.weight": "model-00004-of-00004.safetensors",
328
+ "model.language_model.layers.30.linear_attn.A_log": "model-00004-of-00004.safetensors",
329
+ "model.language_model.layers.30.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
330
+ "model.language_model.layers.30.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
331
+ "model.language_model.layers.30.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
332
+ "model.language_model.layers.30.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
333
+ "model.language_model.layers.30.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
334
+ "model.language_model.layers.30.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
335
+ "model.language_model.layers.30.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
336
+ "model.language_model.layers.30.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
337
+ "model.language_model.layers.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
338
+ "model.language_model.layers.30.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
339
+ "model.language_model.layers.30.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
340
+ "model.language_model.layers.30.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
341
+ "model.language_model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
342
+ "model.language_model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
343
+ "model.language_model.layers.31.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
344
+ "model.language_model.layers.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
345
+ "model.language_model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
346
+ "model.language_model.layers.31.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
347
+ "model.language_model.layers.31.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
348
+ "model.language_model.layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
349
+ "model.language_model.layers.31.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
350
+ "model.language_model.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
351
+ "model.language_model.layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
352
+ "model.language_model.layers.4.input_layernorm.weight": "model-00002-of-00004.safetensors",
353
+ "model.language_model.layers.4.linear_attn.A_log": "model-00002-of-00004.safetensors",
354
+ "model.language_model.layers.4.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
355
+ "model.language_model.layers.4.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
356
+ "model.language_model.layers.4.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
357
+ "model.language_model.layers.4.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
358
+ "model.language_model.layers.4.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
359
+ "model.language_model.layers.4.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
360
+ "model.language_model.layers.4.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
361
+ "model.language_model.layers.4.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
362
+ "model.language_model.layers.4.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
363
+ "model.language_model.layers.4.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
364
+ "model.language_model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
365
+ "model.language_model.layers.4.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
366
+ "model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
367
+ "model.language_model.layers.5.linear_attn.A_log": "model-00002-of-00004.safetensors",
368
+ "model.language_model.layers.5.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
369
+ "model.language_model.layers.5.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
370
+ "model.language_model.layers.5.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
371
+ "model.language_model.layers.5.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
372
+ "model.language_model.layers.5.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
373
+ "model.language_model.layers.5.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
374
+ "model.language_model.layers.5.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
375
+ "model.language_model.layers.5.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
376
+ "model.language_model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
377
+ "model.language_model.layers.5.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
378
+ "model.language_model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
379
+ "model.language_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
380
+ "model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
381
+ "model.language_model.layers.6.linear_attn.A_log": "model-00002-of-00004.safetensors",
382
+ "model.language_model.layers.6.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
383
+ "model.language_model.layers.6.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
384
+ "model.language_model.layers.6.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
385
+ "model.language_model.layers.6.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
386
+ "model.language_model.layers.6.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
387
+ "model.language_model.layers.6.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
388
+ "model.language_model.layers.6.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
389
+ "model.language_model.layers.6.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
390
+ "model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
391
+ "model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
392
+ "model.language_model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
393
+ "model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
394
+ "model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
395
+ "model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
396
+ "model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
397
+ "model.language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
398
+ "model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
399
+ "model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
400
+ "model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
401
+ "model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
402
+ "model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
403
+ "model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
404
+ "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
405
+ "model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
406
+ "model.language_model.layers.8.linear_attn.A_log": "model-00002-of-00004.safetensors",
407
+ "model.language_model.layers.8.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
408
+ "model.language_model.layers.8.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
409
+ "model.language_model.layers.8.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
410
+ "model.language_model.layers.8.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
411
+ "model.language_model.layers.8.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
412
+ "model.language_model.layers.8.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
413
+ "model.language_model.layers.8.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
414
+ "model.language_model.layers.8.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
415
+ "model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
416
+ "model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
417
+ "model.language_model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
418
+ "model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
419
+ "model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
420
+ "model.language_model.layers.9.linear_attn.A_log": "model-00002-of-00004.safetensors",
421
+ "model.language_model.layers.9.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
422
+ "model.language_model.layers.9.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
423
+ "model.language_model.layers.9.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
424
+ "model.language_model.layers.9.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
425
+ "model.language_model.layers.9.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
426
+ "model.language_model.layers.9.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
427
+ "model.language_model.layers.9.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
428
+ "model.language_model.layers.9.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
429
+ "model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
430
+ "model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
431
+ "model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
432
+ "model.language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
433
+ "model.language_model.norm.weight": "model-00004-of-00004.safetensors",
434
+ "model.visual.blocks.0.attn.proj.bias": "model-00004-of-00004.safetensors",
435
+ "model.visual.blocks.0.attn.proj.weight": "model-00004-of-00004.safetensors",
436
+ "model.visual.blocks.0.attn.qkv.bias": "model-00004-of-00004.safetensors",
437
+ "model.visual.blocks.0.attn.qkv.weight": "model-00004-of-00004.safetensors",
438
+ "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
439
+ "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
440
+ "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
441
+ "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
442
+ "model.visual.blocks.0.norm1.bias": "model-00004-of-00004.safetensors",
443
+ "model.visual.blocks.0.norm1.weight": "model-00004-of-00004.safetensors",
444
+ "model.visual.blocks.0.norm2.bias": "model-00004-of-00004.safetensors",
445
+ "model.visual.blocks.0.norm2.weight": "model-00004-of-00004.safetensors",
446
+ "model.visual.blocks.1.attn.proj.bias": "model-00004-of-00004.safetensors",
447
+ "model.visual.blocks.1.attn.proj.weight": "model-00004-of-00004.safetensors",
448
+ "model.visual.blocks.1.attn.qkv.bias": "model-00004-of-00004.safetensors",
449
+ "model.visual.blocks.1.attn.qkv.weight": "model-00004-of-00004.safetensors",
450
+ "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
451
+ "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
452
+ "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
453
+ "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
454
+ "model.visual.blocks.1.norm1.bias": "model-00004-of-00004.safetensors",
455
+ "model.visual.blocks.1.norm1.weight": "model-00004-of-00004.safetensors",
456
+ "model.visual.blocks.1.norm2.bias": "model-00004-of-00004.safetensors",
457
+ "model.visual.blocks.1.norm2.weight": "model-00004-of-00004.safetensors",
458
+ "model.visual.blocks.10.attn.proj.bias": "model-00004-of-00004.safetensors",
459
+ "model.visual.blocks.10.attn.proj.weight": "model-00004-of-00004.safetensors",
460
+ "model.visual.blocks.10.attn.qkv.bias": "model-00004-of-00004.safetensors",
461
+ "model.visual.blocks.10.attn.qkv.weight": "model-00004-of-00004.safetensors",
462
+ "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
463
+ "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
464
+ "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
465
+ "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
466
+ "model.visual.blocks.10.norm1.bias": "model-00004-of-00004.safetensors",
467
+ "model.visual.blocks.10.norm1.weight": "model-00004-of-00004.safetensors",
468
+ "model.visual.blocks.10.norm2.bias": "model-00004-of-00004.safetensors",
469
+ "model.visual.blocks.10.norm2.weight": "model-00004-of-00004.safetensors",
470
+ "model.visual.blocks.11.attn.proj.bias": "model-00004-of-00004.safetensors",
471
+ "model.visual.blocks.11.attn.proj.weight": "model-00004-of-00004.safetensors",
472
+ "model.visual.blocks.11.attn.qkv.bias": "model-00004-of-00004.safetensors",
473
+ "model.visual.blocks.11.attn.qkv.weight": "model-00004-of-00004.safetensors",
474
+ "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
475
+ "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
476
+ "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
477
+ "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
478
+ "model.visual.blocks.11.norm1.bias": "model-00004-of-00004.safetensors",
479
+ "model.visual.blocks.11.norm1.weight": "model-00004-of-00004.safetensors",
480
+ "model.visual.blocks.11.norm2.bias": "model-00004-of-00004.safetensors",
481
+ "model.visual.blocks.11.norm2.weight": "model-00004-of-00004.safetensors",
482
+ "model.visual.blocks.12.attn.proj.bias": "model-00004-of-00004.safetensors",
483
+ "model.visual.blocks.12.attn.proj.weight": "model-00004-of-00004.safetensors",
484
+ "model.visual.blocks.12.attn.qkv.bias": "model-00004-of-00004.safetensors",
485
+ "model.visual.blocks.12.attn.qkv.weight": "model-00004-of-00004.safetensors",
486
+ "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
487
+ "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
488
+ "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
489
+ "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
490
+ "model.visual.blocks.12.norm1.bias": "model-00004-of-00004.safetensors",
491
+ "model.visual.blocks.12.norm1.weight": "model-00004-of-00004.safetensors",
492
+ "model.visual.blocks.12.norm2.bias": "model-00004-of-00004.safetensors",
493
+ "model.visual.blocks.12.norm2.weight": "model-00004-of-00004.safetensors",
494
+ "model.visual.blocks.13.attn.proj.bias": "model-00004-of-00004.safetensors",
495
+ "model.visual.blocks.13.attn.proj.weight": "model-00004-of-00004.safetensors",
496
+ "model.visual.blocks.13.attn.qkv.bias": "model-00004-of-00004.safetensors",
497
+ "model.visual.blocks.13.attn.qkv.weight": "model-00004-of-00004.safetensors",
498
+ "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
499
+ "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
500
+ "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
501
+ "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
502
+ "model.visual.blocks.13.norm1.bias": "model-00004-of-00004.safetensors",
503
+ "model.visual.blocks.13.norm1.weight": "model-00004-of-00004.safetensors",
504
+ "model.visual.blocks.13.norm2.bias": "model-00004-of-00004.safetensors",
505
+ "model.visual.blocks.13.norm2.weight": "model-00004-of-00004.safetensors",
506
+ "model.visual.blocks.14.attn.proj.bias": "model-00004-of-00004.safetensors",
507
+ "model.visual.blocks.14.attn.proj.weight": "model-00004-of-00004.safetensors",
508
+ "model.visual.blocks.14.attn.qkv.bias": "model-00004-of-00004.safetensors",
509
+ "model.visual.blocks.14.attn.qkv.weight": "model-00004-of-00004.safetensors",
510
+ "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
511
+ "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
512
+ "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
513
+ "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
514
+ "model.visual.blocks.14.norm1.bias": "model-00004-of-00004.safetensors",
515
+ "model.visual.blocks.14.norm1.weight": "model-00004-of-00004.safetensors",
516
+ "model.visual.blocks.14.norm2.bias": "model-00004-of-00004.safetensors",
517
+ "model.visual.blocks.14.norm2.weight": "model-00004-of-00004.safetensors",
518
+ "model.visual.blocks.15.attn.proj.bias": "model-00004-of-00004.safetensors",
519
+ "model.visual.blocks.15.attn.proj.weight": "model-00004-of-00004.safetensors",
520
+ "model.visual.blocks.15.attn.qkv.bias": "model-00004-of-00004.safetensors",
521
+ "model.visual.blocks.15.attn.qkv.weight": "model-00004-of-00004.safetensors",
522
+ "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
523
+ "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
524
+ "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
525
+ "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
526
+ "model.visual.blocks.15.norm1.bias": "model-00004-of-00004.safetensors",
527
+ "model.visual.blocks.15.norm1.weight": "model-00004-of-00004.safetensors",
528
+ "model.visual.blocks.15.norm2.bias": "model-00004-of-00004.safetensors",
529
+ "model.visual.blocks.15.norm2.weight": "model-00004-of-00004.safetensors",
530
+ "model.visual.blocks.16.attn.proj.bias": "model-00004-of-00004.safetensors",
531
+ "model.visual.blocks.16.attn.proj.weight": "model-00004-of-00004.safetensors",
532
+ "model.visual.blocks.16.attn.qkv.bias": "model-00004-of-00004.safetensors",
533
+ "model.visual.blocks.16.attn.qkv.weight": "model-00004-of-00004.safetensors",
534
+ "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
535
+ "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
536
+ "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
537
+ "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
538
+ "model.visual.blocks.16.norm1.bias": "model-00004-of-00004.safetensors",
539
+ "model.visual.blocks.16.norm1.weight": "model-00004-of-00004.safetensors",
540
+ "model.visual.blocks.16.norm2.bias": "model-00004-of-00004.safetensors",
541
+ "model.visual.blocks.16.norm2.weight": "model-00004-of-00004.safetensors",
542
+ "model.visual.blocks.17.attn.proj.bias": "model-00004-of-00004.safetensors",
543
+ "model.visual.blocks.17.attn.proj.weight": "model-00004-of-00004.safetensors",
544
+ "model.visual.blocks.17.attn.qkv.bias": "model-00004-of-00004.safetensors",
545
+ "model.visual.blocks.17.attn.qkv.weight": "model-00004-of-00004.safetensors",
546
+ "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
547
+ "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
548
+ "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
549
+ "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
550
+ "model.visual.blocks.17.norm1.bias": "model-00004-of-00004.safetensors",
551
+ "model.visual.blocks.17.norm1.weight": "model-00004-of-00004.safetensors",
552
+ "model.visual.blocks.17.norm2.bias": "model-00004-of-00004.safetensors",
553
+ "model.visual.blocks.17.norm2.weight": "model-00004-of-00004.safetensors",
554
+ "model.visual.blocks.18.attn.proj.bias": "model-00004-of-00004.safetensors",
555
+ "model.visual.blocks.18.attn.proj.weight": "model-00004-of-00004.safetensors",
556
+ "model.visual.blocks.18.attn.qkv.bias": "model-00004-of-00004.safetensors",
557
+ "model.visual.blocks.18.attn.qkv.weight": "model-00004-of-00004.safetensors",
558
+ "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
559
+ "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
560
+ "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
561
+ "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
562
+ "model.visual.blocks.18.norm1.bias": "model-00004-of-00004.safetensors",
563
+ "model.visual.blocks.18.norm1.weight": "model-00004-of-00004.safetensors",
564
+ "model.visual.blocks.18.norm2.bias": "model-00004-of-00004.safetensors",
565
+ "model.visual.blocks.18.norm2.weight": "model-00004-of-00004.safetensors",
566
+ "model.visual.blocks.19.attn.proj.bias": "model-00004-of-00004.safetensors",
567
+ "model.visual.blocks.19.attn.proj.weight": "model-00004-of-00004.safetensors",
568
+ "model.visual.blocks.19.attn.qkv.bias": "model-00004-of-00004.safetensors",
569
+ "model.visual.blocks.19.attn.qkv.weight": "model-00004-of-00004.safetensors",
570
+ "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
571
+ "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
572
+ "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
573
+ "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
574
+ "model.visual.blocks.19.norm1.bias": "model-00004-of-00004.safetensors",
575
+ "model.visual.blocks.19.norm1.weight": "model-00004-of-00004.safetensors",
576
+ "model.visual.blocks.19.norm2.bias": "model-00004-of-00004.safetensors",
577
+ "model.visual.blocks.19.norm2.weight": "model-00004-of-00004.safetensors",
578
+ "model.visual.blocks.2.attn.proj.bias": "model-00004-of-00004.safetensors",
579
+ "model.visual.blocks.2.attn.proj.weight": "model-00004-of-00004.safetensors",
580
+ "model.visual.blocks.2.attn.qkv.bias": "model-00004-of-00004.safetensors",
581
+ "model.visual.blocks.2.attn.qkv.weight": "model-00004-of-00004.safetensors",
582
+ "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
583
+ "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
584
+ "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
585
+ "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
586
+ "model.visual.blocks.2.norm1.bias": "model-00004-of-00004.safetensors",
587
+ "model.visual.blocks.2.norm1.weight": "model-00004-of-00004.safetensors",
588
+ "model.visual.blocks.2.norm2.bias": "model-00004-of-00004.safetensors",
589
+ "model.visual.blocks.2.norm2.weight": "model-00004-of-00004.safetensors",
590
+ "model.visual.blocks.20.attn.proj.bias": "model-00004-of-00004.safetensors",
591
+ "model.visual.blocks.20.attn.proj.weight": "model-00004-of-00004.safetensors",
592
+ "model.visual.blocks.20.attn.qkv.bias": "model-00004-of-00004.safetensors",
593
+ "model.visual.blocks.20.attn.qkv.weight": "model-00004-of-00004.safetensors",
594
+ "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
595
+ "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
596
+ "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
597
+ "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
598
+ "model.visual.blocks.20.norm1.bias": "model-00004-of-00004.safetensors",
599
+ "model.visual.blocks.20.norm1.weight": "model-00004-of-00004.safetensors",
600
+ "model.visual.blocks.20.norm2.bias": "model-00004-of-00004.safetensors",
601
+ "model.visual.blocks.20.norm2.weight": "model-00004-of-00004.safetensors",
602
+ "model.visual.blocks.21.attn.proj.bias": "model-00004-of-00004.safetensors",
603
+ "model.visual.blocks.21.attn.proj.weight": "model-00004-of-00004.safetensors",
604
+ "model.visual.blocks.21.attn.qkv.bias": "model-00004-of-00004.safetensors",
605
+ "model.visual.blocks.21.attn.qkv.weight": "model-00004-of-00004.safetensors",
606
+ "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
607
+ "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
608
+ "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
609
+ "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
610
+ "model.visual.blocks.21.norm1.bias": "model-00004-of-00004.safetensors",
611
+ "model.visual.blocks.21.norm1.weight": "model-00004-of-00004.safetensors",
612
+ "model.visual.blocks.21.norm2.bias": "model-00004-of-00004.safetensors",
613
+ "model.visual.blocks.21.norm2.weight": "model-00004-of-00004.safetensors",
614
+ "model.visual.blocks.22.attn.proj.bias": "model-00004-of-00004.safetensors",
615
+ "model.visual.blocks.22.attn.proj.weight": "model-00004-of-00004.safetensors",
616
+ "model.visual.blocks.22.attn.qkv.bias": "model-00004-of-00004.safetensors",
617
+ "model.visual.blocks.22.attn.qkv.weight": "model-00004-of-00004.safetensors",
618
+ "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
619
+ "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
620
+ "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
621
+ "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
622
+ "model.visual.blocks.22.norm1.bias": "model-00004-of-00004.safetensors",
623
+ "model.visual.blocks.22.norm1.weight": "model-00004-of-00004.safetensors",
624
+ "model.visual.blocks.22.norm2.bias": "model-00004-of-00004.safetensors",
625
+ "model.visual.blocks.22.norm2.weight": "model-00004-of-00004.safetensors",
626
+ "model.visual.blocks.23.attn.proj.bias": "model-00004-of-00004.safetensors",
627
+ "model.visual.blocks.23.attn.proj.weight": "model-00004-of-00004.safetensors",
628
+ "model.visual.blocks.23.attn.qkv.bias": "model-00004-of-00004.safetensors",
629
+ "model.visual.blocks.23.attn.qkv.weight": "model-00004-of-00004.safetensors",
630
+ "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
631
+ "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
632
+ "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
633
+ "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
634
+ "model.visual.blocks.23.norm1.bias": "model-00004-of-00004.safetensors",
635
+ "model.visual.blocks.23.norm1.weight": "model-00004-of-00004.safetensors",
636
+ "model.visual.blocks.23.norm2.bias": "model-00004-of-00004.safetensors",
637
+ "model.visual.blocks.23.norm2.weight": "model-00004-of-00004.safetensors",
638
+ "model.visual.blocks.24.attn.proj.bias": "model-00004-of-00004.safetensors",
639
+ "model.visual.blocks.24.attn.proj.weight": "model-00004-of-00004.safetensors",
640
+ "model.visual.blocks.24.attn.qkv.bias": "model-00004-of-00004.safetensors",
641
+ "model.visual.blocks.24.attn.qkv.weight": "model-00004-of-00004.safetensors",
642
+ "model.visual.blocks.24.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
643
+ "model.visual.blocks.24.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
644
+ "model.visual.blocks.24.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
645
+ "model.visual.blocks.24.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
646
+ "model.visual.blocks.24.norm1.bias": "model-00004-of-00004.safetensors",
647
+ "model.visual.blocks.24.norm1.weight": "model-00004-of-00004.safetensors",
648
+ "model.visual.blocks.24.norm2.bias": "model-00004-of-00004.safetensors",
649
+ "model.visual.blocks.24.norm2.weight": "model-00004-of-00004.safetensors",
650
+ "model.visual.blocks.25.attn.proj.bias": "model-00004-of-00004.safetensors",
651
+ "model.visual.blocks.25.attn.proj.weight": "model-00004-of-00004.safetensors",
652
+ "model.visual.blocks.25.attn.qkv.bias": "model-00004-of-00004.safetensors",
653
+ "model.visual.blocks.25.attn.qkv.weight": "model-00004-of-00004.safetensors",
654
+ "model.visual.blocks.25.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
655
+ "model.visual.blocks.25.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
656
+ "model.visual.blocks.25.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
657
+ "model.visual.blocks.25.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
658
+ "model.visual.blocks.25.norm1.bias": "model-00004-of-00004.safetensors",
659
+ "model.visual.blocks.25.norm1.weight": "model-00004-of-00004.safetensors",
660
+ "model.visual.blocks.25.norm2.bias": "model-00004-of-00004.safetensors",
661
+ "model.visual.blocks.25.norm2.weight": "model-00004-of-00004.safetensors",
662
+ "model.visual.blocks.26.attn.proj.bias": "model-00004-of-00004.safetensors",
663
+ "model.visual.blocks.26.attn.proj.weight": "model-00004-of-00004.safetensors",
664
+ "model.visual.blocks.26.attn.qkv.bias": "model-00004-of-00004.safetensors",
665
+ "model.visual.blocks.26.attn.qkv.weight": "model-00004-of-00004.safetensors",
666
+ "model.visual.blocks.26.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
667
+ "model.visual.blocks.26.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
668
+ "model.visual.blocks.26.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
669
+ "model.visual.blocks.26.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
670
+ "model.visual.blocks.26.norm1.bias": "model-00004-of-00004.safetensors",
671
+ "model.visual.blocks.26.norm1.weight": "model-00004-of-00004.safetensors",
672
+ "model.visual.blocks.26.norm2.bias": "model-00004-of-00004.safetensors",
673
+ "model.visual.blocks.26.norm2.weight": "model-00004-of-00004.safetensors",
674
+ "model.visual.blocks.3.attn.proj.bias": "model-00004-of-00004.safetensors",
675
+ "model.visual.blocks.3.attn.proj.weight": "model-00004-of-00004.safetensors",
676
+ "model.visual.blocks.3.attn.qkv.bias": "model-00004-of-00004.safetensors",
677
+ "model.visual.blocks.3.attn.qkv.weight": "model-00004-of-00004.safetensors",
678
+ "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
679
+ "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
680
+ "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
681
+ "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
682
+ "model.visual.blocks.3.norm1.bias": "model-00004-of-00004.safetensors",
683
+ "model.visual.blocks.3.norm1.weight": "model-00004-of-00004.safetensors",
684
+ "model.visual.blocks.3.norm2.bias": "model-00004-of-00004.safetensors",
685
+ "model.visual.blocks.3.norm2.weight": "model-00004-of-00004.safetensors",
686
+ "model.visual.blocks.4.attn.proj.bias": "model-00004-of-00004.safetensors",
687
+ "model.visual.blocks.4.attn.proj.weight": "model-00004-of-00004.safetensors",
688
+ "model.visual.blocks.4.attn.qkv.bias": "model-00004-of-00004.safetensors",
689
+ "model.visual.blocks.4.attn.qkv.weight": "model-00004-of-00004.safetensors",
690
+ "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
691
+ "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
692
+ "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
693
+ "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
694
+ "model.visual.blocks.4.norm1.bias": "model-00004-of-00004.safetensors",
695
+ "model.visual.blocks.4.norm1.weight": "model-00004-of-00004.safetensors",
696
+ "model.visual.blocks.4.norm2.bias": "model-00004-of-00004.safetensors",
697
+ "model.visual.blocks.4.norm2.weight": "model-00004-of-00004.safetensors",
698
+ "model.visual.blocks.5.attn.proj.bias": "model-00004-of-00004.safetensors",
699
+ "model.visual.blocks.5.attn.proj.weight": "model-00004-of-00004.safetensors",
700
+ "model.visual.blocks.5.attn.qkv.bias": "model-00004-of-00004.safetensors",
701
+ "model.visual.blocks.5.attn.qkv.weight": "model-00004-of-00004.safetensors",
702
+ "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
703
+ "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
704
+ "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
705
+ "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
706
+ "model.visual.blocks.5.norm1.bias": "model-00004-of-00004.safetensors",
707
+ "model.visual.blocks.5.norm1.weight": "model-00004-of-00004.safetensors",
708
+ "model.visual.blocks.5.norm2.bias": "model-00004-of-00004.safetensors",
709
+ "model.visual.blocks.5.norm2.weight": "model-00004-of-00004.safetensors",
710
+ "model.visual.blocks.6.attn.proj.bias": "model-00004-of-00004.safetensors",
711
+ "model.visual.blocks.6.attn.proj.weight": "model-00004-of-00004.safetensors",
712
+ "model.visual.blocks.6.attn.qkv.bias": "model-00004-of-00004.safetensors",
713
+ "model.visual.blocks.6.attn.qkv.weight": "model-00004-of-00004.safetensors",
714
+ "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
715
+ "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
716
+ "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
717
+ "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
718
+ "model.visual.blocks.6.norm1.bias": "model-00004-of-00004.safetensors",
719
+ "model.visual.blocks.6.norm1.weight": "model-00004-of-00004.safetensors",
720
+ "model.visual.blocks.6.norm2.bias": "model-00004-of-00004.safetensors",
721
+ "model.visual.blocks.6.norm2.weight": "model-00004-of-00004.safetensors",
722
+ "model.visual.blocks.7.attn.proj.bias": "model-00004-of-00004.safetensors",
723
+ "model.visual.blocks.7.attn.proj.weight": "model-00004-of-00004.safetensors",
724
+ "model.visual.blocks.7.attn.qkv.bias": "model-00004-of-00004.safetensors",
725
+ "model.visual.blocks.7.attn.qkv.weight": "model-00004-of-00004.safetensors",
726
+ "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
727
+ "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
728
+ "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
729
+ "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
730
+ "model.visual.blocks.7.norm1.bias": "model-00004-of-00004.safetensors",
731
+ "model.visual.blocks.7.norm1.weight": "model-00004-of-00004.safetensors",
732
+ "model.visual.blocks.7.norm2.bias": "model-00004-of-00004.safetensors",
733
+ "model.visual.blocks.7.norm2.weight": "model-00004-of-00004.safetensors",
734
+ "model.visual.blocks.8.attn.proj.bias": "model-00004-of-00004.safetensors",
735
+ "model.visual.blocks.8.attn.proj.weight": "model-00004-of-00004.safetensors",
736
+ "model.visual.blocks.8.attn.qkv.bias": "model-00004-of-00004.safetensors",
737
+ "model.visual.blocks.8.attn.qkv.weight": "model-00004-of-00004.safetensors",
738
+ "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
739
+ "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
740
+ "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
741
+ "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
742
+ "model.visual.blocks.8.norm1.bias": "model-00004-of-00004.safetensors",
743
+ "model.visual.blocks.8.norm1.weight": "model-00004-of-00004.safetensors",
744
+ "model.visual.blocks.8.norm2.bias": "model-00004-of-00004.safetensors",
745
+ "model.visual.blocks.8.norm2.weight": "model-00004-of-00004.safetensors",
746
+ "model.visual.blocks.9.attn.proj.bias": "model-00004-of-00004.safetensors",
747
+ "model.visual.blocks.9.attn.proj.weight": "model-00004-of-00004.safetensors",
748
+ "model.visual.blocks.9.attn.qkv.bias": "model-00004-of-00004.safetensors",
749
+ "model.visual.blocks.9.attn.qkv.weight": "model-00004-of-00004.safetensors",
750
+ "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
751
+ "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
752
+ "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
753
+ "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
754
+ "model.visual.blocks.9.norm1.bias": "model-00004-of-00004.safetensors",
755
+ "model.visual.blocks.9.norm1.weight": "model-00004-of-00004.safetensors",
756
+ "model.visual.blocks.9.norm2.bias": "model-00004-of-00004.safetensors",
757
+ "model.visual.blocks.9.norm2.weight": "model-00004-of-00004.safetensors",
758
+ "model.visual.merger.linear_fc1.bias": "model-00004-of-00004.safetensors",
759
+ "model.visual.merger.linear_fc1.weight": "model-00004-of-00004.safetensors",
760
+ "model.visual.merger.linear_fc2.bias": "model-00004-of-00004.safetensors",
761
+ "model.visual.merger.linear_fc2.weight": "model-00004-of-00004.safetensors",
762
+ "model.visual.merger.norm.bias": "model-00004-of-00004.safetensors",
763
+ "model.visual.merger.norm.weight": "model-00004-of-00004.safetensors",
764
+ "model.visual.patch_embed.proj.bias": "model-00004-of-00004.safetensors",
765
+ "model.visual.patch_embed.proj.weight": "model-00004-of-00004.safetensors",
766
+ "model.visual.pos_embed.weight": "model-00004-of-00004.safetensors"
767
+ }
768
+ }
a4_fixed_images/round_3/preprocessor_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "size": {
3
+ "longest_edge": 16777216,
4
+ "shortest_edge": 65536
5
+ },
6
+ "patch_size": 16,
7
+ "temporal_patch_size": 2,
8
+ "merge_size": 2,
9
+ "image_mean": [
10
+ 0.5,
11
+ 0.5,
12
+ 0.5
13
+ ],
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "processor_class": "Qwen3VLProcessor",
20
+ "image_processor_type": "Qwen2VLImageProcessorFast"
21
+ }
a4_fixed_images/round_3/processor_config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_processor": {
3
+ "do_convert_rgb": true,
4
+ "do_normalize": true,
5
+ "do_rescale": true,
6
+ "do_resize": true,
7
+ "image_mean": [
8
+ 0.5,
9
+ 0.5,
10
+ 0.5
11
+ ],
12
+ "image_processor_type": "Qwen2VLImageProcessor",
13
+ "image_std": [
14
+ 0.5,
15
+ 0.5,
16
+ 0.5
17
+ ],
18
+ "merge_size": 2,
19
+ "patch_size": 16,
20
+ "resample": 3,
21
+ "rescale_factor": 0.00392156862745098,
22
+ "size": {
23
+ "longest_edge": 16777216,
24
+ "shortest_edge": 65536
25
+ },
26
+ "temporal_patch_size": 2
27
+ },
28
+ "processor_class": "Qwen3VLProcessor",
29
+ "video_processor": {
30
+ "do_convert_rgb": true,
31
+ "do_normalize": true,
32
+ "do_rescale": true,
33
+ "do_resize": true,
34
+ "do_sample_frames": true,
35
+ "fps": 2,
36
+ "image_mean": [
37
+ 0.5,
38
+ 0.5,
39
+ 0.5
40
+ ],
41
+ "image_std": [
42
+ 0.5,
43
+ 0.5,
44
+ 0.5
45
+ ],
46
+ "max_frames": 768,
47
+ "merge_size": 2,
48
+ "min_frames": 4,
49
+ "patch_size": 16,
50
+ "resample": 3,
51
+ "rescale_factor": 0.00392156862745098,
52
+ "return_metadata": false,
53
+ "size": {
54
+ "longest_edge": 25165824,
55
+ "shortest_edge": 4096
56
+ },
57
+ "temporal_patch_size": 2,
58
+ "video_processor_type": "Qwen3VLVideoProcessor"
59
+ }
60
+ }
a4_fixed_images/round_3/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
3
+ size 19989325
a4_fixed_images/round_3/tokenizer_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "audio_bos_token": "<|audio_start|>",
4
+ "audio_eos_token": "<|audio_end|>",
5
+ "audio_token": "<|audio_pad|>",
6
+ "backend": "tokenizers",
7
+ "bos_token": null,
8
+ "clean_up_tokenization_spaces": false,
9
+ "eos_token": "<|im_end|>",
10
+ "errors": "replace",
11
+ "image_token": "<|image_pad|>",
12
+ "is_local": true,
13
+ "local_files_only": true,
14
+ "model_max_length": 262144,
15
+ "model_specific_special_tokens": {
16
+ "audio_bos_token": "<|audio_start|>",
17
+ "audio_eos_token": "<|audio_end|>",
18
+ "audio_token": "<|audio_pad|>",
19
+ "image_token": "<|image_pad|>",
20
+ "video_token": "<|video_pad|>",
21
+ "vision_bos_token": "<|vision_start|>",
22
+ "vision_eos_token": "<|vision_end|>"
23
+ },
24
+ "pad_token": "<|endoftext|>",
25
+ "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
26
+ "processor_class": "Qwen3VLProcessor",
27
+ "split_special_tokens": false,
28
+ "tokenizer_class": "Qwen2Tokenizer",
29
+ "unk_token": null,
30
+ "video_token": "<|video_pad|>",
31
+ "vision_bos_token": "<|vision_start|>",
32
+ "vision_eos_token": "<|vision_end|>"
33
+ }
a4_fixed_images/round_3/trainer_state.json ADDED
@@ -0,0 +1,2454 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 80.0,
7
+ "global_step": 160,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "clip_ratio/high_max": 0.0,
14
+ "clip_ratio/high_mean": 0.0,
15
+ "clip_ratio/low_mean": 0.0,
16
+ "clip_ratio/low_min": 0.0,
17
+ "clip_ratio/region_mean": 0.0,
18
+ "completions/clipped_ratio": 0.23828125,
19
+ "completions/max_length": 2048.0,
20
+ "completions/mean_length": 935.46875,
21
+ "completions/min_length": 76.0,
22
+ "epoch": 0.00625,
23
+ "frac_reward_zero_std": 0.21875,
24
+ "grad_norm": 3.2994388780733765,
25
+ "kl": 0.0,
26
+ "learning_rate": 2e-07,
27
+ "loss": -1.30385160446167e-08,
28
+ "reward": 0.41796875,
29
+ "reward_std": 0.3712368607521057,
30
+ "rewards/MajorityAccuracy/mean": 0.41796875,
31
+ "rewards/MajorityAccuracy/std": 0.49419113993644714,
32
+ "step": 1,
33
+ "step_time": 208.80678155180067
34
+ },
35
+ {
36
+ "clip_ratio/high_max": 0.0,
37
+ "clip_ratio/high_mean": 0.0,
38
+ "clip_ratio/low_mean": 0.0,
39
+ "clip_ratio/low_min": 0.0,
40
+ "clip_ratio/region_mean": 0.0,
41
+ "epoch": 0.0125,
42
+ "grad_norm": 2.516025743851983,
43
+ "kl": 0.0,
44
+ "learning_rate": 4e-07,
45
+ "loss": -1.1175870895385742e-08,
46
+ "step": 2,
47
+ "step_time": 24.09924700949341
48
+ },
49
+ {
50
+ "clip_ratio/high_max": 0.0005341880605556071,
51
+ "clip_ratio/high_mean": 0.0002442317781969905,
52
+ "clip_ratio/low_mean": 0.00015300837549148127,
53
+ "clip_ratio/low_min": 0.0,
54
+ "clip_ratio/region_mean": 0.00039724015368847176,
55
+ "epoch": 0.01875,
56
+ "grad_norm": 2.377564034216767,
57
+ "kl": 0.0001605375964572886,
58
+ "learning_rate": 6e-07,
59
+ "loss": 0.00020832280279137194,
60
+ "step": 3,
61
+ "step_time": 24.30531121790409
62
+ },
63
+ {
64
+ "clip_ratio/high_max": 0.0014513588685076684,
65
+ "clip_ratio/high_mean": 0.00045179521112004295,
66
+ "clip_ratio/low_mean": 0.00017769893747754395,
67
+ "clip_ratio/low_min": 0.0,
68
+ "clip_ratio/region_mean": 0.0006294941485975869,
69
+ "epoch": 0.025,
70
+ "grad_norm": 1.9937000526242146,
71
+ "kl": 0.0001644781787035754,
72
+ "learning_rate": 8e-07,
73
+ "loss": -0.0001656178355915472,
74
+ "step": 4,
75
+ "step_time": 24.889284912031144
76
+ },
77
+ {
78
+ "clip_ratio/high_max": 0.0015514300903305411,
79
+ "clip_ratio/high_mean": 0.0003878575225826353,
80
+ "clip_ratio/low_mean": 0.0006487977007054724,
81
+ "clip_ratio/low_min": 0.0,
82
+ "clip_ratio/region_mean": 0.00103665521601215,
83
+ "epoch": 0.03125,
84
+ "grad_norm": 3.4895693900546547,
85
+ "kl": 0.0002582098422863055,
86
+ "learning_rate": 1e-06,
87
+ "loss": 0.00012415536912158132,
88
+ "step": 5,
89
+ "step_time": 24.60476123401895
90
+ },
91
+ {
92
+ "clip_ratio/high_max": 0.004190663588815369,
93
+ "clip_ratio/high_mean": 0.0010942035041807685,
94
+ "clip_ratio/low_mean": 0.0006524196815007599,
95
+ "clip_ratio/low_min": 0.0,
96
+ "clip_ratio/region_mean": 0.0017466231693106238,
97
+ "epoch": 0.0375,
98
+ "grad_norm": 3.444562012388541,
99
+ "kl": 0.00035197375109419227,
100
+ "learning_rate": 9.998973021172564e-07,
101
+ "loss": 0.00019859150052070618,
102
+ "step": 6,
103
+ "step_time": 24.403202696703374
104
+ },
105
+ {
106
+ "clip_ratio/high_max": 0.008019437140319496,
107
+ "clip_ratio/high_mean": 0.0023243519972311333,
108
+ "clip_ratio/low_mean": 9.48189408518374e-05,
109
+ "clip_ratio/low_min": 0.0,
110
+ "clip_ratio/region_mean": 0.0024191709380829707,
111
+ "epoch": 0.04375,
112
+ "grad_norm": 4.294293356165707,
113
+ "kl": 0.0004991115529264789,
114
+ "learning_rate": 9.99589250656446e-07,
115
+ "loss": -6.124246283434331e-06,
116
+ "step": 7,
117
+ "step_time": 24.045550470706075
118
+ },
119
+ {
120
+ "clip_ratio/high_max": 0.003822049795417115,
121
+ "clip_ratio/high_mean": 0.0010009009783971123,
122
+ "clip_ratio/low_mean": 0.0010260162525810301,
123
+ "clip_ratio/low_min": 0.0,
124
+ "clip_ratio/region_mean": 0.0020269172382541,
125
+ "epoch": 0.05,
126
+ "grad_norm": 2.098909159630269,
127
+ "kl": 0.0002858805255527841,
128
+ "learning_rate": 9.990759721625005e-07,
129
+ "loss": -0.00011144764721393585,
130
+ "step": 8,
131
+ "step_time": 24.82261642953381
132
+ },
133
+ {
134
+ "clip_ratio/high_max": 0.0,
135
+ "clip_ratio/high_mean": 0.0,
136
+ "clip_ratio/low_mean": 0.0,
137
+ "clip_ratio/low_min": 0.0,
138
+ "clip_ratio/region_mean": 0.0,
139
+ "completions/clipped_ratio": 0.265625,
140
+ "completions/max_length": 2048.0,
141
+ "completions/mean_length": 982.640625,
142
+ "completions/min_length": 81.0,
143
+ "epoch": 0.05625,
144
+ "frac_reward_zero_std": 0.28125,
145
+ "grad_norm": 2.2659370346861,
146
+ "kl": 0.00040370586430071853,
147
+ "learning_rate": 9.983576774858775e-07,
148
+ "loss": 4.033970981254242e-06,
149
+ "reward": 0.40625,
150
+ "reward_std": 0.34784403443336487,
151
+ "rewards/MajorityAccuracy/mean": 0.40625,
152
+ "rewards/MajorityAccuracy/std": 0.49209436774253845,
153
+ "step": 9,
154
+ "step_time": 188.1314673894085
155
+ },
156
+ {
157
+ "clip_ratio/high_max": 0.001915207933052443,
158
+ "clip_ratio/high_mean": 0.0006029458927514497,
159
+ "clip_ratio/low_mean": 0.0010016581145464443,
160
+ "clip_ratio/low_min": 0.0,
161
+ "clip_ratio/region_mean": 0.001604603989108,
162
+ "epoch": 0.0625,
163
+ "grad_norm": 4.845811373718803,
164
+ "kl": 0.0009788744428078644,
165
+ "learning_rate": 9.974346616959475e-07,
166
+ "loss": 0.00031795166432857513,
167
+ "step": 10,
168
+ "step_time": 23.786794785875827
169
+ },
170
+ {
171
+ "clip_ratio/high_max": 0.009560231876093894,
172
+ "clip_ratio/high_mean": 0.002650643771630712,
173
+ "clip_ratio/low_mean": 0.0008598252497904468,
174
+ "clip_ratio/low_min": 0.0,
175
+ "clip_ratio/region_mean": 0.003510469014145201,
176
+ "epoch": 0.06875,
177
+ "grad_norm": 4.090148239475799,
178
+ "kl": 0.002955242758616805,
179
+ "learning_rate": 9.963073039597796e-07,
180
+ "loss": 0.0006152431597001851,
181
+ "step": 11,
182
+ "step_time": 22.859326587058604
183
+ },
184
+ {
185
+ "clip_ratio/high_max": 0.002943081854027696,
186
+ "clip_ratio/high_mean": 0.0008393549687752966,
187
+ "clip_ratio/low_mean": 0.0004073173404322006,
188
+ "clip_ratio/low_min": 0.0,
189
+ "clip_ratio/region_mean": 0.0012466723164834548,
190
+ "epoch": 0.075,
191
+ "grad_norm": 1.6383422510841037,
192
+ "kl": 0.001146427748608403,
193
+ "learning_rate": 9.949760673863846e-07,
194
+ "loss": -9.793091157916933e-05,
195
+ "step": 12,
196
+ "step_time": 24.715032179374248
197
+ },
198
+ {
199
+ "clip_ratio/high_max": 0.004491277417400852,
200
+ "clip_ratio/high_mean": 0.0011960641204495914,
201
+ "clip_ratio/low_mean": 0.00333832623437047,
202
+ "clip_ratio/low_min": 6.103515625e-05,
203
+ "clip_ratio/region_mean": 0.004534390405751765,
204
+ "epoch": 0.08125,
205
+ "grad_norm": 2.9722496150827418,
206
+ "kl": 0.001837605464970693,
207
+ "learning_rate": 9.934414988364722e-07,
208
+ "loss": 0.0006493376567959785,
209
+ "step": 13,
210
+ "step_time": 24.871748431120068
211
+ },
212
+ {
213
+ "clip_ratio/high_max": 0.0029557555681094527,
214
+ "clip_ratio/high_mean": 0.000891271760337986,
215
+ "clip_ratio/low_mean": 0.0007694554587942548,
216
+ "clip_ratio/low_min": 0.0,
217
+ "clip_ratio/region_mean": 0.001660727233684156,
218
+ "epoch": 0.0875,
219
+ "grad_norm": 1.6013798797093992,
220
+ "kl": 0.0009790184776647948,
221
+ "learning_rate": 9.917042286978063e-07,
222
+ "loss": 0.00020756019512191415,
223
+ "step": 14,
224
+ "step_time": 25.355771363712847
225
+ },
226
+ {
227
+ "clip_ratio/high_max": 0.0053845888178329915,
228
+ "clip_ratio/high_mean": 0.001999696840357501,
229
+ "clip_ratio/low_mean": 0.003632887499406934,
230
+ "clip_ratio/low_min": 0.0,
231
+ "clip_ratio/region_mean": 0.005632584361592308,
232
+ "epoch": 0.09375,
233
+ "grad_norm": 2.3796807770688067,
234
+ "kl": 0.002431440312648192,
235
+ "learning_rate": 9.897649706262473e-07,
236
+ "loss": 0.0006166249513626099,
237
+ "step": 15,
238
+ "step_time": 24.870181343052536
239
+ },
240
+ {
241
+ "clip_ratio/high_max": 0.005712042388040572,
242
+ "clip_ratio/high_mean": 0.0019426116487011313,
243
+ "clip_ratio/low_mean": 0.0017581438005436212,
244
+ "clip_ratio/low_min": 0.0,
245
+ "clip_ratio/region_mean": 0.0037007554492447525,
246
+ "epoch": 0.1,
247
+ "grad_norm": 1.605830089376638,
248
+ "kl": 0.003803739440627396,
249
+ "learning_rate": 9.87624521252587e-07,
250
+ "loss": 0.0007334449328482151,
251
+ "step": 16,
252
+ "step_time": 24.76658567925915
253
+ },
254
+ {
255
+ "clip_ratio/high_max": 0.0,
256
+ "clip_ratio/high_mean": 0.0,
257
+ "clip_ratio/low_mean": 0.0,
258
+ "clip_ratio/low_min": 0.0,
259
+ "clip_ratio/region_mean": 0.0,
260
+ "completions/clipped_ratio": 0.16796875,
261
+ "completions/max_length": 2048.0,
262
+ "completions/mean_length": 786.41796875,
263
+ "completions/min_length": 69.0,
264
+ "epoch": 0.10625,
265
+ "frac_reward_zero_std": 0.1875,
266
+ "grad_norm": 2.9695669766272097,
267
+ "kl": 0.0035189003974664956,
268
+ "learning_rate": 9.852837598553008e-07,
269
+ "loss": 3.520381142152473e-05,
270
+ "reward": 0.39453125,
271
+ "reward_std": 0.38452082872390747,
272
+ "rewards/MajorityAccuracy/mean": 0.39453125,
273
+ "rewards/MajorityAccuracy/std": 0.48970717191696167,
274
+ "step": 17,
275
+ "step_time": 186.2571491827257
276
+ },
277
+ {
278
+ "clip_ratio/high_max": 0.005008636566344649,
279
+ "clip_ratio/high_mean": 0.001444064822862856,
280
+ "clip_ratio/low_mean": 0.0006362867425195873,
281
+ "clip_ratio/low_min": 0.0,
282
+ "clip_ratio/region_mean": 0.0020803515653824434,
283
+ "epoch": 0.1125,
284
+ "grad_norm": 2.653704609686447,
285
+ "kl": 0.005142666457686573,
286
+ "learning_rate": 9.827436479993468e-07,
287
+ "loss": 0.0001991681638173759,
288
+ "step": 18,
289
+ "step_time": 22.301514303777367
290
+ },
291
+ {
292
+ "clip_ratio/high_max": 0.0014190509682521224,
293
+ "clip_ratio/high_mean": 0.00047585214633727446,
294
+ "clip_ratio/low_mean": 0.0004369059024611488,
295
+ "clip_ratio/low_min": 0.0,
296
+ "clip_ratio/region_mean": 0.0009127580633503385,
297
+ "epoch": 0.11875,
298
+ "grad_norm": 3.7798398787235894,
299
+ "kl": 0.0016869497048901394,
300
+ "learning_rate": 9.800052291411629e-07,
301
+ "loss": 0.00021358951926231384,
302
+ "step": 19,
303
+ "step_time": 25.074343358632177
304
+ },
305
+ {
306
+ "clip_ratio/high_max": 0.00440728290413972,
307
+ "clip_ratio/high_mean": 0.001516119980806252,
308
+ "clip_ratio/low_mean": 0.002492468775017187,
309
+ "clip_ratio/low_min": 0.0,
310
+ "clip_ratio/region_mean": 0.004008588701253757,
311
+ "epoch": 0.125,
312
+ "grad_norm": 3.4051807389869904,
313
+ "kl": 0.004340318351751193,
314
+ "learning_rate": 9.770696282000244e-07,
315
+ "loss": -0.0003863181918859482,
316
+ "step": 20,
317
+ "step_time": 22.834592283237725
318
+ },
319
+ {
320
+ "clip_ratio/high_max": 0.0029197628755355254,
321
+ "clip_ratio/high_mean": 0.0009312015354225878,
322
+ "clip_ratio/low_mean": 0.0034656945354072377,
323
+ "clip_ratio/low_min": 0.0,
324
+ "clip_ratio/region_mean": 0.004396896038088016,
325
+ "epoch": 0.13125,
326
+ "grad_norm": 3.093743771418617,
327
+ "kl": 0.0030462023278232664,
328
+ "learning_rate": 9.739380510959364e-07,
329
+ "loss": 0.0012196926400065422,
330
+ "step": 21,
331
+ "step_time": 23.863958075642586
332
+ },
333
+ {
334
+ "clip_ratio/high_max": 0.009527715243166313,
335
+ "clip_ratio/high_mean": 0.002934813433967065,
336
+ "clip_ratio/low_mean": 0.002745470017543994,
337
+ "clip_ratio/low_min": 0.0,
338
+ "clip_ratio/region_mean": 0.005680283480614889,
339
+ "epoch": 0.1375,
340
+ "grad_norm": 4.734479455372366,
341
+ "kl": 0.006584627495612949,
342
+ "learning_rate": 9.706117842542516e-07,
343
+ "loss": 0.001471108989790082,
344
+ "step": 22,
345
+ "step_time": 25.183104823343456
346
+ },
347
+ {
348
+ "clip_ratio/high_max": 0.012676748818194028,
349
+ "clip_ratio/high_mean": 0.0035877792670362396,
350
+ "clip_ratio/low_mean": 0.0024882884627004387,
351
+ "clip_ratio/low_min": 0.0,
352
+ "clip_ratio/region_mean": 0.006076067918911576,
353
+ "epoch": 0.14375,
354
+ "grad_norm": 3.335872611035554,
355
+ "kl": 0.009207222203258425,
356
+ "learning_rate": 9.670921940772186e-07,
357
+ "loss": 0.0009351514745503664,
358
+ "step": 23,
359
+ "step_time": 24.859260324854404
360
+ },
361
+ {
362
+ "clip_ratio/high_max": 0.005917194532230496,
363
+ "clip_ratio/high_mean": 0.002258967491798103,
364
+ "clip_ratio/low_mean": 0.003973491577198729,
365
+ "clip_ratio/low_min": 0.0,
366
+ "clip_ratio/region_mean": 0.00623245898168534,
367
+ "epoch": 0.15,
368
+ "grad_norm": 2.8844255239753775,
369
+ "kl": 0.0052262264071032405,
370
+ "learning_rate": 9.633807263826744e-07,
371
+ "loss": 0.0007897454779595137,
372
+ "step": 24,
373
+ "step_time": 25.733215983957052
374
+ },
375
+ {
376
+ "clip_ratio/high_max": 0.0,
377
+ "clip_ratio/high_mean": 0.0,
378
+ "clip_ratio/low_mean": 0.0,
379
+ "clip_ratio/low_min": 0.0,
380
+ "clip_ratio/region_mean": 0.0,
381
+ "completions/clipped_ratio": 0.29296875,
382
+ "completions/max_length": 2048.0,
383
+ "completions/mean_length": 988.9296875,
384
+ "completions/min_length": 92.0,
385
+ "epoch": 0.15625,
386
+ "frac_reward_zero_std": 0.46875,
387
+ "grad_norm": 2.0977308705503055,
388
+ "kl": 0.012442333449143916,
389
+ "learning_rate": 9.594789058101153e-07,
390
+ "loss": 0.00012443313607946038,
391
+ "reward": 0.30078125,
392
+ "reward_std": 0.23448193073272705,
393
+ "rewards/MajorityAccuracy/mean": 0.30078125,
394
+ "rewards/MajorityAccuracy/std": 0.45949608087539673,
395
+ "step": 25,
396
+ "step_time": 185.2216110904701
397
+ },
398
+ {
399
+ "clip_ratio/high_max": 0.0004290042706998065,
400
+ "clip_ratio/high_mean": 0.00010725106767495163,
401
+ "clip_ratio/low_mean": 8.82896529219579e-05,
402
+ "clip_ratio/low_min": 0.0,
403
+ "clip_ratio/region_mean": 0.00019554072059690952,
404
+ "epoch": 0.1625,
405
+ "grad_norm": 0.827302182703035,
406
+ "kl": 0.0036683852085843682,
407
+ "learning_rate": 9.55388335194388e-07,
408
+ "loss": 4.549291043076664e-05,
409
+ "step": 26,
410
+ "step_time": 24.834097729995847
411
+ },
412
+ {
413
+ "clip_ratio/high_max": 0.003604056269978173,
414
+ "clip_ratio/high_mean": 0.0009229285242327023,
415
+ "clip_ratio/low_mean": 0.0021996050199959427,
416
+ "clip_ratio/low_min": 0.0,
417
+ "clip_ratio/region_mean": 0.003122533526038751,
418
+ "epoch": 0.16875,
419
+ "grad_norm": 3.589412355754882,
420
+ "kl": 0.010003720468375832,
421
+ "learning_rate": 9.511106949072587e-07,
422
+ "loss": -0.0001631148043088615,
423
+ "step": 27,
424
+ "step_time": 23.916061274707317
425
+ },
426
+ {
427
+ "clip_ratio/high_max": 0.001789596804883331,
428
+ "clip_ratio/high_mean": 0.00044739920122083277,
429
+ "clip_ratio/low_mean": 0.0015249323587340768,
430
+ "clip_ratio/low_min": 0.0,
431
+ "clip_ratio/region_mean": 0.001972331574506825,
432
+ "epoch": 0.175,
433
+ "grad_norm": 1.6782913211446884,
434
+ "kl": 0.010726599430199713,
435
+ "learning_rate": 9.466477421671295e-07,
436
+ "loss": 0.0001096634950954467,
437
+ "step": 28,
438
+ "step_time": 23.473962317220867
439
+ },
440
+ {
441
+ "clip_ratio/high_max": 0.004004015354439616,
442
+ "clip_ratio/high_mean": 0.001001003838609904,
443
+ "clip_ratio/low_mean": 0.0019055970187764615,
444
+ "clip_ratio/low_min": 0.0,
445
+ "clip_ratio/region_mean": 0.0029066008719382808,
446
+ "epoch": 0.18125,
447
+ "grad_norm": 2.5778030588389576,
448
+ "kl": 0.00763463374460116,
449
+ "learning_rate": 9.420013103171891e-07,
450
+ "loss": -0.00012707406131085008,
451
+ "step": 29,
452
+ "step_time": 25.383742638397962
453
+ },
454
+ {
455
+ "clip_ratio/high_max": 0.0029850982245989144,
456
+ "clip_ratio/high_mean": 0.0008239143062382936,
457
+ "clip_ratio/low_mean": 0.001306454447330907,
458
+ "clip_ratio/low_min": 0.0,
459
+ "clip_ratio/region_mean": 0.0021303687535692006,
460
+ "epoch": 0.1875,
461
+ "grad_norm": 3.2085692493390017,
462
+ "kl": 0.010627174691762775,
463
+ "learning_rate": 9.37173308072291e-07,
464
+ "loss": 0.0004268418997526169,
465
+ "step": 30,
466
+ "step_time": 25.078937562648207
467
+ },
468
+ {
469
+ "clip_ratio/high_max": 0.010435085219796747,
470
+ "clip_ratio/high_mean": 0.0035299423325341195,
471
+ "clip_ratio/low_mean": 0.0006730739769409411,
472
+ "clip_ratio/low_min": 0.0,
473
+ "clip_ratio/region_mean": 0.004203016374958679,
474
+ "epoch": 0.19375,
475
+ "grad_norm": 2.7599118175538973,
476
+ "kl": 0.0064775291248224676,
477
+ "learning_rate": 9.321657187348688e-07,
478
+ "loss": 0.00047630106564611197,
479
+ "step": 31,
480
+ "step_time": 25.35646535549313
481
+ },
482
+ {
483
+ "clip_ratio/high_max": 0.003314020170364529,
484
+ "clip_ratio/high_mean": 0.0008285050425911322,
485
+ "clip_ratio/low_mean": 0.0020031664898851886,
486
+ "clip_ratio/low_min": 0.0,
487
+ "clip_ratio/region_mean": 0.002831671547028236,
488
+ "epoch": 0.2,
489
+ "grad_norm": 1.7039664620562431,
490
+ "kl": 0.005384603573475033,
491
+ "learning_rate": 9.269805993802128e-07,
492
+ "loss": 0.0002461112744640559,
493
+ "step": 32,
494
+ "step_time": 25.37204045150429
495
+ },
496
+ {
497
+ "clip_ratio/high_max": 0.0,
498
+ "clip_ratio/high_mean": 0.0,
499
+ "clip_ratio/low_mean": 0.0,
500
+ "clip_ratio/low_min": 0.0,
501
+ "clip_ratio/region_mean": 0.0,
502
+ "completions/clipped_ratio": 0.2265625,
503
+ "completions/max_length": 2048.0,
504
+ "completions/mean_length": 910.87890625,
505
+ "completions/min_length": 50.0,
506
+ "epoch": 0.20625,
507
+ "frac_reward_zero_std": 0.25,
508
+ "grad_norm": 3.4000029412906305,
509
+ "kl": 0.018373101600445807,
510
+ "learning_rate": 9.216200800114411e-07,
511
+ "loss": 0.00018377981905359775,
512
+ "reward": 0.33984375,
513
+ "reward_std": 0.34021925926208496,
514
+ "rewards/MajorityAccuracy/mean": 0.33984375,
515
+ "rewards/MajorityAccuracy/std": 0.47458380460739136,
516
+ "step": 33,
517
+ "step_time": 185.9811329236254
518
+ },
519
+ {
520
+ "clip_ratio/high_max": 0.0031544132507406175,
521
+ "clip_ratio/high_mean": 0.001348100442555733,
522
+ "clip_ratio/low_mean": 0.0009318665252067149,
523
+ "clip_ratio/low_min": 0.0,
524
+ "clip_ratio/region_mean": 0.002279966967762448,
525
+ "epoch": 0.2125,
526
+ "grad_norm": 2.7181148331332845,
527
+ "kl": 0.0103240484604612,
528
+ "learning_rate": 9.160863626845119e-07,
529
+ "loss": 0.00018270686268806458,
530
+ "step": 34,
531
+ "step_time": 23.386239951942116
532
+ },
533
+ {
534
+ "clip_ratio/high_max": 0.00040453075780533254,
535
+ "clip_ratio/high_mean": 0.00010113268945133314,
536
+ "clip_ratio/low_mean": 0.0004365187578514451,
537
+ "clip_ratio/low_min": 0.0,
538
+ "clip_ratio/region_mean": 0.0005376514473027783,
539
+ "epoch": 0.21875,
540
+ "grad_norm": 1.45090984604168,
541
+ "kl": 0.00425730599090457,
542
+ "learning_rate": 9.103817206036382e-07,
543
+ "loss": 0.00012768285523634404,
544
+ "step": 35,
545
+ "step_time": 24.81424072291702
546
+ },
547
+ {
548
+ "clip_ratio/high_max": 0.005089230267913081,
549
+ "clip_ratio/high_mean": 0.0017867508722702041,
550
+ "clip_ratio/low_mean": 0.0007586584179080091,
551
+ "clip_ratio/low_min": 0.0,
552
+ "clip_ratio/region_mean": 0.0025454092101426795,
553
+ "epoch": 0.225,
554
+ "grad_norm": 2.4337148292828443,
555
+ "kl": 0.0070523262256756425,
556
+ "learning_rate": 9.045084971874737e-07,
557
+ "loss": 9.255483746528625e-05,
558
+ "step": 36,
559
+ "step_time": 24.69577978691086
560
+ },
561
+ {
562
+ "clip_ratio/high_max": 0.006382683961419389,
563
+ "clip_ratio/high_mean": 0.0018963671755045652,
564
+ "clip_ratio/low_mean": 0.0012447314002201892,
565
+ "clip_ratio/low_min": 0.0,
566
+ "clip_ratio/region_mean": 0.0031410985393449664,
567
+ "epoch": 0.23125,
568
+ "grad_norm": 1.7567678196798906,
569
+ "kl": 0.006672150979284197,
570
+ "learning_rate": 8.984691051064574e-07,
571
+ "loss": -0.00013057453907094896,
572
+ "step": 37,
573
+ "step_time": 25.178669043350965
574
+ },
575
+ {
576
+ "clip_ratio/high_max": 0.006654171316768043,
577
+ "clip_ratio/high_mean": 0.0019890747316821944,
578
+ "clip_ratio/low_mean": 0.002192627711337991,
579
+ "clip_ratio/low_min": 0.0,
580
+ "clip_ratio/region_mean": 0.0041817024612100795,
581
+ "epoch": 0.2375,
582
+ "grad_norm": 2.720866407452676,
583
+ "kl": 0.010978317528497428,
584
+ "learning_rate": 8.922660252917087e-07,
585
+ "loss": 0.0005555209936574101,
586
+ "step": 38,
587
+ "step_time": 24.057694994378835
588
+ },
589
+ {
590
+ "clip_ratio/high_max": 0.019480244780424982,
591
+ "clip_ratio/high_mean": 0.006209476006915793,
592
+ "clip_ratio/low_mean": 0.002257349329738645,
593
+ "clip_ratio/low_min": 0.0,
594
+ "clip_ratio/region_mean": 0.008466825413051993,
595
+ "epoch": 0.24375,
596
+ "grad_norm": 4.69235662645644,
597
+ "kl": 0.008467482984997332,
598
+ "learning_rate": 8.859018059158809e-07,
599
+ "loss": 0.0009746319847181439,
600
+ "step": 39,
601
+ "step_time": 24.741801417898387
602
+ },
603
+ {
604
+ "clip_ratio/high_max": 0.005690045072697103,
605
+ "clip_ratio/high_mean": 0.0015903716121101752,
606
+ "clip_ratio/low_mean": 0.004083418287336826,
607
+ "clip_ratio/low_min": 0.0004252542566973716,
608
+ "clip_ratio/region_mean": 0.005673789826687425,
609
+ "epoch": 0.25,
610
+ "grad_norm": 2.2919567535316037,
611
+ "kl": 0.008572620630729944,
612
+ "learning_rate": 8.793790613463954e-07,
613
+ "loss": 0.000280626118183136,
614
+ "step": 40,
615
+ "step_time": 24.743270099163055
616
+ },
617
+ {
618
+ "clip_ratio/high_max": 0.0,
619
+ "clip_ratio/high_mean": 0.0,
620
+ "clip_ratio/low_mean": 0.0,
621
+ "clip_ratio/low_min": 0.0,
622
+ "clip_ratio/region_mean": 0.0,
623
+ "completions/clipped_ratio": 0.234375,
624
+ "completions/max_length": 2048.0,
625
+ "completions/mean_length": 985.21484375,
626
+ "completions/min_length": 65.0,
627
+ "epoch": 0.25625,
628
+ "frac_reward_zero_std": 0.375,
629
+ "grad_norm": 1.0287173072294307,
630
+ "kl": 0.003862341429339722,
631
+ "learning_rate": 8.727004710714798e-07,
632
+ "loss": 3.865889084408991e-05,
633
+ "reward": 0.26171875,
634
+ "reward_std": 0.29944002628326416,
635
+ "rewards/MajorityAccuracy/mean": 0.26171875,
636
+ "rewards/MajorityAccuracy/std": 0.4404313564300537,
637
+ "step": 41,
638
+ "step_time": 185.49576449766755
639
+ },
640
+ {
641
+ "clip_ratio/high_max": 0.0009976277069654316,
642
+ "clip_ratio/high_mean": 0.00027974673139397055,
643
+ "clip_ratio/low_mean": 0.00010668823415471707,
644
+ "clip_ratio/low_min": 0.0,
645
+ "clip_ratio/region_mean": 0.0003864349655486876,
646
+ "epoch": 0.2625,
647
+ "grad_norm": 1.385565354037175,
648
+ "kl": 0.019892863696441054,
649
+ "learning_rate": 8.658687785994578e-07,
650
+ "loss": 0.00017663283506408334,
651
+ "step": 42,
652
+ "step_time": 23.76611733622849
653
+ },
654
+ {
655
+ "clip_ratio/high_max": 0.0011721307528205216,
656
+ "clip_ratio/high_mean": 0.00031791325818630867,
657
+ "clip_ratio/low_mean": 0.0002300666892551817,
658
+ "clip_ratio/low_min": 0.0,
659
+ "clip_ratio/region_mean": 0.0005479799474414904,
660
+ "epoch": 0.26875,
661
+ "grad_norm": 0.9911350019854345,
662
+ "kl": 0.004422976140631363,
663
+ "learning_rate": 8.588867903317394e-07,
664
+ "loss": 0.0001597576920175925,
665
+ "step": 43,
666
+ "step_time": 25.020751000382006
667
+ },
668
+ {
669
+ "clip_ratio/high_max": 0.0032965086720651016,
670
+ "clip_ratio/high_mean": 0.0009344963582407217,
671
+ "clip_ratio/low_mean": 0.0011881193131557666,
672
+ "clip_ratio/low_min": 0.0,
673
+ "clip_ratio/region_mean": 0.00212261569686234,
674
+ "epoch": 0.275,
675
+ "grad_norm": 2.2698658706490003,
676
+ "kl": 0.012168462271802127,
677
+ "learning_rate": 8.51757374409974e-07,
678
+ "loss": -3.901873424183577e-05,
679
+ "step": 44,
680
+ "step_time": 23.002621789928526
681
+ },
682
+ {
683
+ "clip_ratio/high_max": 0.0031367281917482615,
684
+ "clip_ratio/high_mean": 0.0007841820479370654,
685
+ "clip_ratio/low_mean": 0.0016289429040625691,
686
+ "clip_ratio/low_min": 0.0,
687
+ "clip_ratio/region_mean": 0.0024131249519996345,
688
+ "epoch": 0.28125,
689
+ "grad_norm": 2.104190085190714,
690
+ "kl": 0.029130531009286642,
691
+ "learning_rate": 8.444834595378433e-07,
692
+ "loss": 0.0006130897090770304,
693
+ "step": 45,
694
+ "step_time": 23.23925462551415
695
+ },
696
+ {
697
+ "clip_ratio/high_max": 0.0034685512946452945,
698
+ "clip_ratio/high_mean": 0.0008968997353804298,
699
+ "clip_ratio/low_mean": 0.0014313349493022542,
700
+ "clip_ratio/low_min": 0.0,
701
+ "clip_ratio/region_mean": 0.0023282346373889595,
702
+ "epoch": 0.2875,
703
+ "grad_norm": 2.132889608494028,
704
+ "kl": 0.0076728290296159685,
705
+ "learning_rate": 8.370680337779736e-07,
706
+ "loss": -8.6526561062783e-05,
707
+ "step": 46,
708
+ "step_time": 24.98702518036589
709
+ },
710
+ {
711
+ "clip_ratio/high_max": 0.0022523720981553197,
712
+ "clip_ratio/high_mean": 0.0007239410479087383,
713
+ "clip_ratio/low_mean": 0.0013540414947783574,
714
+ "clip_ratio/low_min": 0.0,
715
+ "clip_ratio/region_mean": 0.0020779825426870957,
716
+ "epoch": 0.29375,
717
+ "grad_norm": 1.5820475242792866,
718
+ "kl": 0.00704644963843748,
719
+ "learning_rate": 8.295141433244659e-07,
720
+ "loss": -7.381418254226446e-05,
721
+ "step": 47,
722
+ "step_time": 24.67927945777774
723
+ },
724
+ {
725
+ "clip_ratio/high_max": 0.006754414760507643,
726
+ "clip_ratio/high_mean": 0.002449051185976714,
727
+ "clip_ratio/low_mean": 0.005714948434615508,
728
+ "clip_ratio/low_min": 0.00054931640625,
729
+ "clip_ratio/region_mean": 0.008163999649696052,
730
+ "epoch": 0.3,
731
+ "grad_norm": 3.8016304462391193,
732
+ "kl": 0.01264659536536783,
733
+ "learning_rate": 8.218248912515442e-07,
734
+ "loss": 0.002414829097688198,
735
+ "step": 48,
736
+ "step_time": 24.341566421091557
737
+ },
738
+ {
739
+ "clip_ratio/high_max": 0.0,
740
+ "clip_ratio/high_mean": 0.0,
741
+ "clip_ratio/low_mean": 0.0,
742
+ "clip_ratio/low_min": 0.0,
743
+ "clip_ratio/region_mean": 0.0,
744
+ "completions/clipped_ratio": 0.24609375,
745
+ "completions/max_length": 2048.0,
746
+ "completions/mean_length": 978.18359375,
747
+ "completions/min_length": 66.0,
748
+ "epoch": 0.30625,
749
+ "frac_reward_zero_std": 0.34375,
750
+ "grad_norm": 2.2024711306246485,
751
+ "kl": 0.009075262874830514,
752
+ "learning_rate": 8.140034362388397e-07,
753
+ "loss": 9.077224240172654e-05,
754
+ "reward": 0.3125,
755
+ "reward_std": 0.30141592025756836,
756
+ "rewards/MajorityAccuracy/mean": 0.3125,
757
+ "rewards/MajorityAccuracy/std": 0.4644203782081604,
758
+ "step": 49,
759
+ "step_time": 186.0726659167558
760
+ },
761
+ {
762
+ "clip_ratio/high_max": 0.004707420084741898,
763
+ "clip_ratio/high_mean": 0.0013205147588450927,
764
+ "clip_ratio/low_mean": 0.00040804919626680203,
765
+ "clip_ratio/low_min": 0.0,
766
+ "clip_ratio/region_mean": 0.0017285639441979583,
767
+ "epoch": 0.3125,
768
+ "grad_norm": 3.2112321559783426,
769
+ "kl": 0.014715113793499768,
770
+ "learning_rate": 8.060529912738314e-07,
771
+ "loss": 3.467453643679619e-05,
772
+ "step": 50,
773
+ "step_time": 24.227659524418414
774
+ },
775
+ {
776
+ "clip_ratio/high_max": 0.004089088994078338,
777
+ "clip_ratio/high_mean": 0.0012698395585175604,
778
+ "clip_ratio/low_mean": 0.00026257444733346347,
779
+ "clip_ratio/low_min": 0.0,
780
+ "clip_ratio/region_mean": 0.001532414011307992,
781
+ "epoch": 0.31875,
782
+ "grad_norm": 5.03176957379202,
783
+ "kl": 0.013905421597883105,
784
+ "learning_rate": 7.979768223319785e-07,
785
+ "loss": 0.00033030749182216823,
786
+ "step": 51,
787
+ "step_time": 23.92098210658878
788
+ },
789
+ {
790
+ "clip_ratio/high_max": 0.0029202808218542486,
791
+ "clip_ratio/high_mean": 0.0008936827725847252,
792
+ "clip_ratio/low_mean": 0.00108789699152112,
793
+ "clip_ratio/low_min": 0.0,
794
+ "clip_ratio/region_mean": 0.001981579807761591,
795
+ "epoch": 0.325,
796
+ "grad_norm": 2.566194665741442,
797
+ "kl": 0.012587467150297016,
798
+ "learning_rate": 7.897782470350849e-07,
799
+ "loss": -3.842161095235497e-05,
800
+ "step": 52,
801
+ "step_time": 24.970363825093955
802
+ },
803
+ {
804
+ "clip_ratio/high_max": 0.001931259612319991,
805
+ "clip_ratio/high_mean": 0.00048281490307999775,
806
+ "clip_ratio/low_mean": 0.0007483760418836027,
807
+ "clip_ratio/low_min": 0.0,
808
+ "clip_ratio/region_mean": 0.0012311909595155157,
809
+ "epoch": 0.33125,
810
+ "grad_norm": 2.0730319182049373,
811
+ "kl": 0.007133064849767834,
812
+ "learning_rate": 7.814606332884488e-07,
813
+ "loss": -9.978427260648459e-05,
814
+ "step": 53,
815
+ "step_time": 26.087400309275836
816
+ },
817
+ {
818
+ "clip_ratio/high_max": 0.020377097396703903,
819
+ "clip_ratio/high_mean": 0.006483763741925941,
820
+ "clip_ratio/low_mean": 0.003176409052684903,
821
+ "clip_ratio/low_min": 0.0,
822
+ "clip_ratio/region_mean": 0.00966017271275632,
823
+ "epoch": 0.3375,
824
+ "grad_norm": 2.940687172682488,
825
+ "kl": 0.031105898320674896,
826
+ "learning_rate": 7.730273978973552e-07,
827
+ "loss": 0.002576085738837719,
828
+ "step": 54,
829
+ "step_time": 24.78940772730857
830
+ },
831
+ {
832
+ "clip_ratio/high_max": 0.012894722574856132,
833
+ "clip_ratio/high_mean": 0.0042358491773484275,
834
+ "clip_ratio/low_mean": 0.002268853015266359,
835
+ "clip_ratio/low_min": 0.0,
836
+ "clip_ratio/region_mean": 0.006504702148959041,
837
+ "epoch": 0.34375,
838
+ "grad_norm": 4.207529639933832,
839
+ "kl": 0.014494398143142462,
840
+ "learning_rate": 7.644820051634812e-07,
841
+ "loss": 0.0009966231882572174,
842
+ "step": 55,
843
+ "step_time": 23.693179208785295
844
+ },
845
+ {
846
+ "clip_ratio/high_max": 0.008024955342989415,
847
+ "clip_ratio/high_mean": 0.0020062388357473537,
848
+ "clip_ratio/low_mean": 0.0015158068381424528,
849
+ "clip_ratio/low_min": 0.0,
850
+ "clip_ratio/region_mean": 0.003522045699355658,
851
+ "epoch": 0.35,
852
+ "grad_norm": 3.233838059596785,
853
+ "kl": 0.008750205277465284,
854
+ "learning_rate": 7.558279654617912e-07,
855
+ "loss": 0.00035623746225610375,
856
+ "step": 56,
857
+ "step_time": 24.613843394909054
858
+ },
859
+ {
860
+ "clip_ratio/high_max": 0.0,
861
+ "clip_ratio/high_mean": 0.0,
862
+ "clip_ratio/low_mean": 0.0,
863
+ "clip_ratio/low_min": 0.0,
864
+ "clip_ratio/region_mean": 0.0,
865
+ "completions/clipped_ratio": 0.21484375,
866
+ "completions/max_length": 2048.0,
867
+ "completions/mean_length": 853.4375,
868
+ "completions/min_length": 73.0,
869
+ "epoch": 0.35625,
870
+ "frac_reward_zero_std": 0.25,
871
+ "grad_norm": 4.62497313007244,
872
+ "kl": 0.012768905377015471,
873
+ "learning_rate": 7.470688337985029e-07,
874
+ "loss": 0.00012767687439918518,
875
+ "reward": 0.453125,
876
+ "reward_std": 0.34770071506500244,
877
+ "rewards/MajorityAccuracy/mean": 0.453125,
878
+ "rewards/MajorityAccuracy/std": 0.4987730085849762,
879
+ "step": 57,
880
+ "step_time": 185.70756297791377
881
+ },
882
+ {
883
+ "clip_ratio/high_max": 0.003896840615198016,
884
+ "clip_ratio/high_mean": 0.000974210153799504,
885
+ "clip_ratio/low_mean": 0.00048634782251610886,
886
+ "clip_ratio/low_min": 0.0,
887
+ "clip_ratio/region_mean": 0.0014605579781346023,
888
+ "epoch": 0.3625,
889
+ "grad_norm": 3.897141513273689,
890
+ "kl": 0.0081084119156003,
891
+ "learning_rate": 7.382082083507225e-07,
892
+ "loss": -0.00015269707364495844,
893
+ "step": 58,
894
+ "step_time": 24.009666742756963
895
+ },
896
+ {
897
+ "clip_ratio/high_max": 0.004025017282401677,
898
+ "clip_ratio/high_mean": 0.0010629368171066744,
899
+ "clip_ratio/low_mean": 0.0006004366696288344,
900
+ "clip_ratio/low_min": 0.0,
901
+ "clip_ratio/region_mean": 0.001663373519477318,
902
+ "epoch": 0.36875,
903
+ "grad_norm": 3.4272488870680053,
904
+ "kl": 0.012271420389879495,
905
+ "learning_rate": 7.292497289883432e-07,
906
+ "loss": 0.0004984453553333879,
907
+ "step": 59,
908
+ "step_time": 24.927320430520922
909
+ },
910
+ {
911
+ "clip_ratio/high_max": 0.0018005116726271808,
912
+ "clip_ratio/high_mean": 0.0005179151121410541,
913
+ "clip_ratio/low_mean": 0.0012776018120348454,
914
+ "clip_ratio/low_min": 0.0,
915
+ "clip_ratio/region_mean": 0.0017955169241758995,
916
+ "epoch": 0.375,
917
+ "grad_norm": 2.4424434244375584,
918
+ "kl": 0.010324264701921493,
919
+ "learning_rate": 7.201970757788171e-07,
920
+ "loss": 0.00010644421854522079,
921
+ "step": 60,
922
+ "step_time": 25.176113487686962
923
+ },
924
+ {
925
+ "clip_ratio/high_max": 0.0051833186007570475,
926
+ "clip_ratio/high_mean": 0.001725112677377183,
927
+ "clip_ratio/low_mean": 0.0011462995680631138,
928
+ "clip_ratio/low_min": 0.0,
929
+ "clip_ratio/region_mean": 0.002871412245440297,
930
+ "epoch": 0.38125,
931
+ "grad_norm": 3.328105663301918,
932
+ "kl": 0.015592740848660469,
933
+ "learning_rate": 7.110539674754159e-07,
934
+ "loss": 0.0011947103776037693,
935
+ "step": 61,
936
+ "step_time": 23.76721590338275
937
+ },
938
+ {
939
+ "clip_ratio/high_max": 0.00750837211671751,
940
+ "clip_ratio/high_mean": 0.0018770930291793775,
941
+ "clip_ratio/low_mean": 0.0026473012985661626,
942
+ "clip_ratio/low_min": 0.0,
943
+ "clip_ratio/region_mean": 0.004524394404143095,
944
+ "epoch": 0.3875,
945
+ "grad_norm": 4.6739133550372225,
946
+ "kl": 0.03352465410716832,
947
+ "learning_rate": 7.018241599895973e-07,
948
+ "loss": 0.0008287477539852262,
949
+ "step": 62,
950
+ "step_time": 24.98314088024199
951
+ },
952
+ {
953
+ "clip_ratio/high_max": 0.010305540956323966,
954
+ "clip_ratio/high_mean": 0.0027848735844600014,
955
+ "clip_ratio/low_mean": 0.0023718228185316548,
956
+ "clip_ratio/low_min": 0.0,
957
+ "clip_ratio/region_mean": 0.0051566964539233595,
958
+ "epoch": 0.39375,
959
+ "grad_norm": 4.735161863778931,
960
+ "kl": 0.02155363536439836,
961
+ "learning_rate": 6.925114448481088e-07,
962
+ "loss": 0.00023077023797668517,
963
+ "step": 63,
964
+ "step_time": 23.559055018238723
965
+ },
966
+ {
967
+ "clip_ratio/high_max": 0.007336975715588778,
968
+ "clip_ratio/high_mean": 0.0022878354939166456,
969
+ "clip_ratio/low_mean": 0.0014343098446261138,
970
+ "clip_ratio/low_min": 0.0,
971
+ "clip_ratio/region_mean": 0.0037221453385427594,
972
+ "epoch": 0.4,
973
+ "grad_norm": 2.7425939287395216,
974
+ "kl": 0.017463925178162754,
975
+ "learning_rate": 6.831196476354614e-07,
976
+ "loss": 0.00025247145094908774,
977
+ "step": 64,
978
+ "step_time": 25.167045696172863
979
+ },
980
+ {
981
+ "clip_ratio/high_max": 0.0,
982
+ "clip_ratio/high_mean": 0.0,
983
+ "clip_ratio/low_mean": 0.0,
984
+ "clip_ratio/low_min": 0.0,
985
+ "clip_ratio/region_mean": 0.0,
986
+ "completions/clipped_ratio": 0.1796875,
987
+ "completions/max_length": 2048.0,
988
+ "completions/mean_length": 758.0,
989
+ "completions/min_length": 75.0,
990
+ "epoch": 0.40625,
991
+ "frac_reward_zero_std": 0.28125,
992
+ "grad_norm": 1.7153179593675776,
993
+ "kl": 0.01334342232439667,
994
+ "learning_rate": 6.7365262642241e-07,
995
+ "loss": 0.0001334746921202168,
996
+ "reward": 0.4453125,
997
+ "reward_std": 0.3263999819755554,
998
+ "rewards/MajorityAccuracy/mean": 0.4453125,
999
+ "rewards/MajorityAccuracy/std": 0.49797382950782776,
1000
+ "step": 65,
1001
+ "step_time": 180.74631309788674
1002
+ },
1003
+ {
1004
+ "clip_ratio/high_max": 0.0013495661842171103,
1005
+ "clip_ratio/high_mean": 0.00036529333010548726,
1006
+ "clip_ratio/low_mean": 0.0003270307533966843,
1007
+ "clip_ratio/low_min": 0.0,
1008
+ "clip_ratio/region_mean": 0.0006923240871401504,
1009
+ "epoch": 0.4125,
1010
+ "grad_norm": 1.8246082076635182,
1011
+ "kl": 0.012188129127025604,
1012
+ "learning_rate": 6.641142701810931e-07,
1013
+ "loss": 1.5998986782506108e-05,
1014
+ "step": 66,
1015
+ "step_time": 25.04222670663148
1016
+ },
1017
+ {
1018
+ "clip_ratio/high_max": 0.0018610530823934823,
1019
+ "clip_ratio/high_mean": 0.0004652632705983706,
1020
+ "clip_ratio/low_mean": 0.0002085937376250513,
1021
+ "clip_ratio/low_min": 0.0,
1022
+ "clip_ratio/region_mean": 0.0006738570082234219,
1023
+ "epoch": 0.41875,
1024
+ "grad_norm": 4.029074700014686,
1025
+ "kl": 0.014837535680271685,
1026
+ "learning_rate": 6.545084971874736e-07,
1027
+ "loss": 0.0003878355782944709,
1028
+ "step": 67,
1029
+ "step_time": 24.610105445142835
1030
+ },
1031
+ {
1032
+ "clip_ratio/high_max": 0.0081853736191988,
1033
+ "clip_ratio/high_mean": 0.002276742277899757,
1034
+ "clip_ratio/low_mean": 0.0021597580289380858,
1035
+ "clip_ratio/low_min": 0.0,
1036
+ "clip_ratio/region_mean": 0.004436500239535235,
1037
+ "epoch": 0.425,
1038
+ "grad_norm": 6.973653132546046,
1039
+ "kl": 0.04464558605104685,
1040
+ "learning_rate": 6.448392534117461e-07,
1041
+ "loss": 0.0003402717411518097,
1042
+ "step": 68,
1043
+ "step_time": 22.73716756887734
1044
+ },
1045
+ {
1046
+ "clip_ratio/high_max": 0.005366766708903015,
1047
+ "clip_ratio/high_mean": 0.001676107247476466,
1048
+ "clip_ratio/low_mean": 0.0045221080363262445,
1049
+ "clip_ratio/low_min": 0.0,
1050
+ "clip_ratio/region_mean": 0.006198215312906541,
1051
+ "epoch": 0.43125,
1052
+ "grad_norm": 3.36410123100141,
1053
+ "kl": 0.017930401023477316,
1054
+ "learning_rate": 6.351105108973644e-07,
1055
+ "loss": 0.0009741833200678229,
1056
+ "step": 69,
1057
+ "step_time": 21.939505197107792
1058
+ },
1059
+ {
1060
+ "clip_ratio/high_max": 0.005550288726226427,
1061
+ "clip_ratio/high_mean": 0.0019257591957284603,
1062
+ "clip_ratio/low_mean": 0.0030402787087950855,
1063
+ "clip_ratio/low_min": 0.0,
1064
+ "clip_ratio/region_mean": 0.004966038017300889,
1065
+ "epoch": 0.4375,
1066
+ "grad_norm": 3.210279819436838,
1067
+ "kl": 0.031130210496485233,
1068
+ "learning_rate": 6.253262661293602e-07,
1069
+ "loss": 0.0011797696352005005,
1070
+ "step": 70,
1071
+ "step_time": 24.76788749312982
1072
+ },
1073
+ {
1074
+ "clip_ratio/high_max": 0.011064380596508272,
1075
+ "clip_ratio/high_mean": 0.0032777741471363697,
1076
+ "clip_ratio/low_mean": 0.0022007066872902215,
1077
+ "clip_ratio/low_min": 0.0,
1078
+ "clip_ratio/region_mean": 0.005478480859892443,
1079
+ "epoch": 0.44375,
1080
+ "grad_norm": 4.919112250878259,
1081
+ "kl": 0.017998081748373806,
1082
+ "learning_rate": 6.154905383926216e-07,
1083
+ "loss": 0.0016150573501363397,
1084
+ "step": 71,
1085
+ "step_time": 25.65763571532443
1086
+ },
1087
+ {
1088
+ "clip_ratio/high_max": 0.005855489464011043,
1089
+ "clip_ratio/high_mean": 0.0014960556873120368,
1090
+ "clip_ratio/low_mean": 0.0024922539450926706,
1091
+ "clip_ratio/low_min": 0.0,
1092
+ "clip_ratio/region_mean": 0.003988309603300877,
1093
+ "epoch": 0.45,
1094
+ "grad_norm": 3.5154453243184154,
1095
+ "kl": 0.01818527898285538,
1096
+ "learning_rate": 6.056073681208037e-07,
1097
+ "loss": 0.0005847337888553739,
1098
+ "step": 72,
1099
+ "step_time": 24.781591073144227
1100
+ },
1101
+ {
1102
+ "clip_ratio/high_max": 0.0,
1103
+ "clip_ratio/high_mean": 0.0,
1104
+ "clip_ratio/low_mean": 0.0,
1105
+ "clip_ratio/low_min": 0.0,
1106
+ "clip_ratio/region_mean": 0.0,
1107
+ "completions/clipped_ratio": 0.23046875,
1108
+ "completions/max_length": 2048.0,
1109
+ "completions/mean_length": 958.28515625,
1110
+ "completions/min_length": 64.0,
1111
+ "epoch": 0.45625,
1112
+ "frac_reward_zero_std": 0.25,
1113
+ "grad_norm": 1.2234413468047642,
1114
+ "kl": 0.03309860941953957,
1115
+ "learning_rate": 5.956808152365532e-07,
1116
+ "loss": 0.0003308813611511141,
1117
+ "reward": 0.37109375,
1118
+ "reward_std": 0.33744850754737854,
1119
+ "rewards/MajorityAccuracy/mean": 0.37109375,
1120
+ "rewards/MajorityAccuracy/std": 0.48404380679130554,
1121
+ "step": 73,
1122
+ "step_time": 187.68038295721635
1123
+ },
1124
+ {
1125
+ "clip_ratio/high_max": 0.007406555625493638,
1126
+ "clip_ratio/high_mean": 0.0021588798372249585,
1127
+ "clip_ratio/low_mean": 0.0005711145531677175,
1128
+ "clip_ratio/low_min": 0.0,
1129
+ "clip_ratio/region_mean": 0.0027299943758407608,
1130
+ "epoch": 0.4625,
1131
+ "grad_norm": 3.0192983202317345,
1132
+ "kl": 0.013361586316023022,
1133
+ "learning_rate": 5.857149574837268e-07,
1134
+ "loss": 0.0004102354869246483,
1135
+ "step": 74,
1136
+ "step_time": 25.174202038440853
1137
+ },
1138
+ {
1139
+ "clip_ratio/high_max": 0.0025386976485606283,
1140
+ "clip_ratio/high_mean": 0.0007293958406080492,
1141
+ "clip_ratio/low_mean": 0.0011896327778231353,
1142
+ "clip_ratio/low_min": 6.103515625e-05,
1143
+ "clip_ratio/region_mean": 0.0019190285747754388,
1144
+ "epoch": 0.46875,
1145
+ "grad_norm": 2.5906114584239353,
1146
+ "kl": 0.013300799648277462,
1147
+ "learning_rate": 5.757138887522883e-07,
1148
+ "loss": 0.00019716843962669373,
1149
+ "step": 75,
1150
+ "step_time": 25.167831495869905
1151
+ },
1152
+ {
1153
+ "clip_ratio/high_max": 0.005397733737481758,
1154
+ "clip_ratio/high_mean": 0.0017472582912887447,
1155
+ "clip_ratio/low_mean": 0.0008986478060251102,
1156
+ "clip_ratio/low_min": 0.0,
1157
+ "clip_ratio/region_mean": 0.002645906148245558,
1158
+ "epoch": 0.475,
1159
+ "grad_norm": 5.67900549804578,
1160
+ "kl": 0.03538850462064147,
1161
+ "learning_rate": 5.656817173965732e-07,
1162
+ "loss": 0.0014598534908145666,
1163
+ "step": 76,
1164
+ "step_time": 24.415067180991173
1165
+ },
1166
+ {
1167
+ "clip_ratio/high_max": 0.0012199118209537119,
1168
+ "clip_ratio/high_mean": 0.00030497795523842797,
1169
+ "clip_ratio/low_mean": 0.000677750231261598,
1170
+ "clip_ratio/low_min": 0.0,
1171
+ "clip_ratio/region_mean": 0.000982728182862047,
1172
+ "epoch": 0.48125,
1173
+ "grad_norm": 1.4930151657741069,
1174
+ "kl": 0.01065082720015198,
1175
+ "learning_rate": 5.556225645476118e-07,
1176
+ "loss": 1.879111005109735e-05,
1177
+ "step": 77,
1178
+ "step_time": 25.081283334176987
1179
+ },
1180
+ {
1181
+ "clip_ratio/high_max": 0.0049706818390404806,
1182
+ "clip_ratio/high_mean": 0.0019025111796509009,
1183
+ "clip_ratio/low_mean": 0.004778426897246391,
1184
+ "clip_ratio/low_min": 0.0,
1185
+ "clip_ratio/region_mean": 0.006680938065983355,
1186
+ "epoch": 0.4875,
1187
+ "grad_norm": 4.367608860177029,
1188
+ "kl": 0.02829379285685718,
1189
+ "learning_rate": 5.455405624202032e-07,
1190
+ "loss": 0.0015850560739636421,
1191
+ "step": 78,
1192
+ "step_time": 24.012428423389792
1193
+ },
1194
+ {
1195
+ "clip_ratio/high_max": 0.0031596092303516343,
1196
+ "clip_ratio/high_mean": 0.0008662148866278585,
1197
+ "clip_ratio/low_mean": 0.0032945944694802165,
1198
+ "clip_ratio/low_min": 0.0,
1199
+ "clip_ratio/region_mean": 0.004160809359746054,
1200
+ "epoch": 0.49375,
1201
+ "grad_norm": 3.7041699600924,
1202
+ "kl": 0.024105938617140055,
1203
+ "learning_rate": 5.354398526154365e-07,
1204
+ "loss": 0.0005642974865622818,
1205
+ "step": 79,
1206
+ "step_time": 24.183080974500626
1207
+ },
1208
+ {
1209
+ "clip_ratio/high_max": 0.002896510995924473,
1210
+ "clip_ratio/high_mean": 0.0008780083153396845,
1211
+ "clip_ratio/low_mean": 0.0009032042871695012,
1212
+ "clip_ratio/low_min": 0.0,
1213
+ "clip_ratio/region_mean": 0.0017812126025091857,
1214
+ "epoch": 0.5,
1215
+ "grad_norm": 2.46535135176018,
1216
+ "kl": 0.017134349909611046,
1217
+ "learning_rate": 5.253245844193564e-07,
1218
+ "loss": 0.0005194220575504005,
1219
+ "step": 80,
1220
+ "step_time": 24.49795059300959
1221
+ },
1222
+ {
1223
+ "clip_ratio/high_max": 0.0,
1224
+ "clip_ratio/high_mean": 0.0,
1225
+ "clip_ratio/low_mean": 0.0,
1226
+ "clip_ratio/low_min": 0.0,
1227
+ "clip_ratio/region_mean": 0.0,
1228
+ "completions/clipped_ratio": 0.15234375,
1229
+ "completions/max_length": 2048.0,
1230
+ "completions/mean_length": 681.375,
1231
+ "completions/min_length": 83.0,
1232
+ "epoch": 0.50625,
1233
+ "frac_reward_zero_std": 0.25,
1234
+ "grad_norm": 3.7906678874591457,
1235
+ "kl": 0.023944684537127614,
1236
+ "learning_rate": 5.151989130984714e-07,
1237
+ "loss": 0.0002395894262008369,
1238
+ "reward": 0.5078125,
1239
+ "reward_std": 0.3197173476219177,
1240
+ "rewards/MajorityAccuracy/mean": 0.5078125,
1241
+ "rewards/MajorityAccuracy/std": 0.5009182691574097,
1242
+ "step": 81,
1243
+ "step_time": 180.91004595020786
1244
+ },
1245
+ {
1246
+ "clip_ratio/high_max": 0.003093614272074774,
1247
+ "clip_ratio/high_mean": 0.0008637214777991176,
1248
+ "clip_ratio/low_mean": 0.00024133233091561124,
1249
+ "clip_ratio/low_min": 0.0,
1250
+ "clip_ratio/region_mean": 0.0011050538159906864,
1251
+ "epoch": 0.5125,
1252
+ "grad_norm": 3.479409368657873,
1253
+ "kl": 0.028679235372692347,
1254
+ "learning_rate": 5.050669981928055e-07,
1255
+ "loss": -8.225702913478017e-06,
1256
+ "step": 82,
1257
+ "step_time": 22.89637992531061
1258
+ },
1259
+ {
1260
+ "clip_ratio/high_max": 0.004978135199053213,
1261
+ "clip_ratio/high_mean": 0.001705200418655295,
1262
+ "clip_ratio/low_mean": 0.0008961745534179499,
1263
+ "clip_ratio/low_min": 0.0,
1264
+ "clip_ratio/region_mean": 0.0026013749302364886,
1265
+ "epoch": 0.51875,
1266
+ "grad_norm": 4.667790805087449,
1267
+ "kl": 0.014629742479883134,
1268
+ "learning_rate": 4.949330018071946e-07,
1269
+ "loss": 0.00046710018068552017,
1270
+ "step": 83,
1271
+ "step_time": 23.829858273267746
1272
+ },
1273
+ {
1274
+ "clip_ratio/high_max": 0.007115483283996582,
1275
+ "clip_ratio/high_mean": 0.0020536573720164597,
1276
+ "clip_ratio/low_mean": 0.0006662621017312631,
1277
+ "clip_ratio/low_min": 0.0,
1278
+ "clip_ratio/region_mean": 0.002719919415540062,
1279
+ "epoch": 0.525,
1280
+ "grad_norm": 4.966286845349483,
1281
+ "kl": 0.03259548032656312,
1282
+ "learning_rate": 4.848010869015287e-07,
1283
+ "loss": 0.0003560303011909127,
1284
+ "step": 84,
1285
+ "step_time": 24.245297060348094
1286
+ },
1287
+ {
1288
+ "clip_ratio/high_max": 0.002715230148169212,
1289
+ "clip_ratio/high_mean": 0.000678807537042303,
1290
+ "clip_ratio/low_mean": 4.57763671875e-05,
1291
+ "clip_ratio/low_min": 0.0,
1292
+ "clip_ratio/region_mean": 0.000724583904229803,
1293
+ "epoch": 0.53125,
1294
+ "grad_norm": 1.5611602835077227,
1295
+ "kl": 0.02022536814911291,
1296
+ "learning_rate": 4.746754155806437e-07,
1297
+ "loss": 0.00042446726001799107,
1298
+ "step": 85,
1299
+ "step_time": 22.878454454708844
1300
+ },
1301
+ {
1302
+ "clip_ratio/high_max": 0.011813084041932598,
1303
+ "clip_ratio/high_mean": 0.004460452335479204,
1304
+ "clip_ratio/low_mean": 0.0007811165996827185,
1305
+ "clip_ratio/low_min": 0.0,
1306
+ "clip_ratio/region_mean": 0.005241568956989795,
1307
+ "epoch": 0.5375,
1308
+ "grad_norm": 5.598217946028612,
1309
+ "kl": 0.027438436402007937,
1310
+ "learning_rate": 4.645601473845635e-07,
1311
+ "loss": 0.0020504435524344444,
1312
+ "step": 86,
1313
+ "step_time": 24.765506824478507
1314
+ },
1315
+ {
1316
+ "clip_ratio/high_max": 0.008153254297212698,
1317
+ "clip_ratio/high_mean": 0.0024481417531205807,
1318
+ "clip_ratio/low_mean": 0.0010723996674641967,
1319
+ "clip_ratio/low_min": 0.0,
1320
+ "clip_ratio/region_mean": 0.0035205414351366926,
1321
+ "epoch": 0.54375,
1322
+ "grad_norm": 4.566349737533934,
1323
+ "kl": 0.0345097875688225,
1324
+ "learning_rate": 4.544594375797968e-07,
1325
+ "loss": 0.00197477824985981,
1326
+ "step": 87,
1327
+ "step_time": 24.84957295516506
1328
+ },
1329
+ {
1330
+ "clip_ratio/high_max": 0.001858463219832629,
1331
+ "clip_ratio/high_mean": 0.0005323542427504435,
1332
+ "clip_ratio/low_mean": 0.003152641700580716,
1333
+ "clip_ratio/low_min": 0.0,
1334
+ "clip_ratio/region_mean": 0.003684995914227329,
1335
+ "epoch": 0.55,
1336
+ "grad_norm": 1.9531922161179756,
1337
+ "kl": 0.02273144223727286,
1338
+ "learning_rate": 4.443774354523882e-07,
1339
+ "loss": 0.0002295393933309242,
1340
+ "step": 88,
1341
+ "step_time": 25.297407489735633
1342
+ },
1343
+ {
1344
+ "clip_ratio/high_max": 0.0,
1345
+ "clip_ratio/high_mean": 0.0,
1346
+ "clip_ratio/low_mean": 0.0,
1347
+ "clip_ratio/low_min": 0.0,
1348
+ "clip_ratio/region_mean": 0.0,
1349
+ "completions/clipped_ratio": 0.23046875,
1350
+ "completions/max_length": 2048.0,
1351
+ "completions/mean_length": 947.08203125,
1352
+ "completions/min_length": 51.0,
1353
+ "epoch": 0.55625,
1354
+ "frac_reward_zero_std": 0.21875,
1355
+ "grad_norm": 3.9645446444872237,
1356
+ "kl": 0.03308751783333719,
1357
+ "learning_rate": 4.3431828260342675e-07,
1358
+ "loss": 0.0003309529274702072,
1359
+ "reward": 0.42578125,
1360
+ "reward_std": 0.377422571182251,
1361
+ "rewards/MajorityAccuracy/mean": 0.42578125,
1362
+ "rewards/MajorityAccuracy/std": 0.49542948603630066,
1363
+ "step": 89,
1364
+ "step_time": 184.47492833761498
1365
+ },
1366
+ {
1367
+ "clip_ratio/high_max": 0.002989657034049742,
1368
+ "clip_ratio/high_mean": 0.0007788845505274367,
1369
+ "clip_ratio/low_mean": 0.0005794188145955559,
1370
+ "clip_ratio/low_min": 0.0,
1371
+ "clip_ratio/region_mean": 0.0013583033651229925,
1372
+ "epoch": 0.5625,
1373
+ "grad_norm": 1.8632283978178106,
1374
+ "kl": 0.02002240251749754,
1375
+ "learning_rate": 4.242861112477118e-07,
1376
+ "loss": -0.00018292292952537537,
1377
+ "step": 90,
1378
+ "step_time": 24.308552390895784
1379
+ },
1380
+ {
1381
+ "clip_ratio/high_max": 0.0009566748340148479,
1382
+ "clip_ratio/high_mean": 0.00029547501617344096,
1383
+ "clip_ratio/low_mean": 0.0003545680028764764,
1384
+ "clip_ratio/low_min": 0.0,
1385
+ "clip_ratio/region_mean": 0.0006500430281448644,
1386
+ "epoch": 0.56875,
1387
+ "grad_norm": 2.5961834699590014,
1388
+ "kl": 0.015785084338858724,
1389
+ "learning_rate": 4.1428504251627325e-07,
1390
+ "loss": 0.00020076071086805314,
1391
+ "step": 91,
1392
+ "step_time": 25.398491187486798
1393
+ },
1394
+ {
1395
+ "clip_ratio/high_max": 0.000943836203077808,
1396
+ "clip_ratio/high_mean": 0.000235959050769452,
1397
+ "clip_ratio/low_mean": 0.00022361135779647157,
1398
+ "clip_ratio/low_min": 0.0,
1399
+ "clip_ratio/region_mean": 0.00045957040856592357,
1400
+ "epoch": 0.575,
1401
+ "grad_norm": 2.2025042667094152,
1402
+ "kl": 0.011239038547500968,
1403
+ "learning_rate": 4.0431918476344685e-07,
1404
+ "loss": 0.00015828953473828733,
1405
+ "step": 92,
1406
+ "step_time": 25.078916994854808
1407
+ },
1408
+ {
1409
+ "clip_ratio/high_max": 0.0027589463352342136,
1410
+ "clip_ratio/high_mean": 0.0007116972283256473,
1411
+ "clip_ratio/low_mean": 0.00025243509298888966,
1412
+ "clip_ratio/low_min": 0.0,
1413
+ "clip_ratio/region_mean": 0.0009641323194955476,
1414
+ "epoch": 0.58125,
1415
+ "grad_norm": 1.0922742731313364,
1416
+ "kl": 0.011261551408097148,
1417
+ "learning_rate": 3.943926318791963e-07,
1418
+ "loss": 0.00042822223622351885,
1419
+ "step": 93,
1420
+ "step_time": 24.85713968379423
1421
+ },
1422
+ {
1423
+ "clip_ratio/high_max": 0.008716845259186812,
1424
+ "clip_ratio/high_mean": 0.0027385113535274286,
1425
+ "clip_ratio/low_mean": 0.0007698228655499406,
1426
+ "clip_ratio/low_min": 0.0,
1427
+ "clip_ratio/region_mean": 0.003508334222715348,
1428
+ "epoch": 0.5875,
1429
+ "grad_norm": 3.6997753500828914,
1430
+ "kl": 0.04267858201637864,
1431
+ "learning_rate": 3.845094616073783e-07,
1432
+ "loss": 0.001056480105035007,
1433
+ "step": 94,
1434
+ "step_time": 22.899330105166882
1435
+ },
1436
+ {
1437
+ "clip_ratio/high_max": 0.0055412921064998955,
1438
+ "clip_ratio/high_mean": 0.0020053060434293,
1439
+ "clip_ratio/low_mean": 0.0005379818794608582,
1440
+ "clip_ratio/low_min": 0.0,
1441
+ "clip_ratio/region_mean": 0.0025432879629079252,
1442
+ "epoch": 0.59375,
1443
+ "grad_norm": 4.5523887498160365,
1444
+ "kl": 0.024657392059452832,
1445
+ "learning_rate": 3.7467373387063964e-07,
1446
+ "loss": 0.0006675906479358673,
1447
+ "step": 95,
1448
+ "step_time": 23.3978268513456
1449
+ },
1450
+ {
1451
+ "clip_ratio/high_max": 0.0019045915105380118,
1452
+ "clip_ratio/high_mean": 0.0005441075772978365,
1453
+ "clip_ratio/low_mean": 0.0006824154188507237,
1454
+ "clip_ratio/low_min": 0.0,
1455
+ "clip_ratio/region_mean": 0.0012265230034245178,
1456
+ "epoch": 0.6,
1457
+ "grad_norm": 3.1997310246750166,
1458
+ "kl": 0.01303628773894161,
1459
+ "learning_rate": 3.648894891026358e-07,
1460
+ "loss": 0.0002713138237595558,
1461
+ "step": 96,
1462
+ "step_time": 25.011431260965765
1463
+ },
1464
+ {
1465
+ "clip_ratio/high_max": 0.0,
1466
+ "clip_ratio/high_mean": 0.0,
1467
+ "clip_ratio/low_mean": 0.0,
1468
+ "clip_ratio/low_min": 0.0,
1469
+ "clip_ratio/region_mean": 0.0,
1470
+ "completions/clipped_ratio": 0.26171875,
1471
+ "completions/max_length": 2048.0,
1472
+ "completions/mean_length": 927.55859375,
1473
+ "completions/min_length": 67.0,
1474
+ "epoch": 0.60625,
1475
+ "frac_reward_zero_std": 0.4375,
1476
+ "grad_norm": 2.746830182234399,
1477
+ "kl": 0.0162498417776078,
1478
+ "learning_rate": 3.5516074658825397e-07,
1479
+ "loss": 0.00016247414168901742,
1480
+ "reward": 0.390625,
1481
+ "reward_std": 0.23475275933742523,
1482
+ "rewards/MajorityAccuracy/mean": 0.390625,
1483
+ "rewards/MajorityAccuracy/std": 0.48884618282318115,
1484
+ "step": 97,
1485
+ "step_time": 186.276470198296
1486
+ },
1487
+ {
1488
+ "clip_ratio/high_max": 0.00042662114719860256,
1489
+ "clip_ratio/high_mean": 0.00010665528679965064,
1490
+ "clip_ratio/low_mean": 0.00043476466089487076,
1491
+ "clip_ratio/low_min": 0.0,
1492
+ "clip_ratio/region_mean": 0.0005414199476945214,
1493
+ "epoch": 0.6125,
1494
+ "grad_norm": 2.8294558723194903,
1495
+ "kl": 0.037818039301782846,
1496
+ "learning_rate": 3.454915028125263e-07,
1497
+ "loss": 0.00035748054506257176,
1498
+ "step": 98,
1499
+ "step_time": 23.018607531208545
1500
+ },
1501
+ {
1502
+ "clip_ratio/high_max": 0.0,
1503
+ "clip_ratio/high_mean": 0.0,
1504
+ "clip_ratio/low_mean": 0.0,
1505
+ "clip_ratio/low_min": 0.0,
1506
+ "clip_ratio/region_mean": 0.0,
1507
+ "epoch": 0.61875,
1508
+ "grad_norm": 0.055361921613878734,
1509
+ "kl": 0.012385692331008613,
1510
+ "learning_rate": 3.3588572981890684e-07,
1511
+ "loss": 0.0001239300618181005,
1512
+ "step": 99,
1513
+ "step_time": 24.896389742847532
1514
+ },
1515
+ {
1516
+ "clip_ratio/high_max": 0.004809682359336875,
1517
+ "clip_ratio/high_mean": 0.0015151679872360546,
1518
+ "clip_ratio/low_mean": 0.0005800919461762533,
1519
+ "clip_ratio/low_min": 0.0,
1520
+ "clip_ratio/region_mean": 0.002095259915222414,
1521
+ "epoch": 0.625,
1522
+ "grad_norm": 2.591678658552652,
1523
+ "kl": 0.027717803488485515,
1524
+ "learning_rate": 3.263473735775899e-07,
1525
+ "loss": 0.00016563631652388722,
1526
+ "step": 100,
1527
+ "step_time": 24.149877541232854
1528
+ },
1529
+ {
1530
+ "clip_ratio/high_max": 0.0008795171015663072,
1531
+ "clip_ratio/high_mean": 0.0002198792753915768,
1532
+ "clip_ratio/low_mean": 0.0008711664777365513,
1533
+ "clip_ratio/low_min": 0.0,
1534
+ "clip_ratio/region_mean": 0.001091045734938234,
1535
+ "epoch": 0.63125,
1536
+ "grad_norm": 2.2551953384788788,
1537
+ "kl": 0.02133840532042086,
1538
+ "learning_rate": 3.1688035236453865e-07,
1539
+ "loss": 0.00011316684685880318,
1540
+ "step": 101,
1541
+ "step_time": 24.340119928121567
1542
+ },
1543
+ {
1544
+ "clip_ratio/high_max": 0.003992271493189037,
1545
+ "clip_ratio/high_mean": 0.0011380018695490435,
1546
+ "clip_ratio/low_mean": 0.0005955125379841775,
1547
+ "clip_ratio/low_min": 0.0,
1548
+ "clip_ratio/region_mean": 0.001733514407533221,
1549
+ "epoch": 0.6375,
1550
+ "grad_norm": 2.044003125262282,
1551
+ "kl": 0.012874316773377359,
1552
+ "learning_rate": 3.0748855515189096e-07,
1553
+ "loss": 0.00014772173017263412,
1554
+ "step": 102,
1555
+ "step_time": 25.199218209367245
1556
+ },
1557
+ {
1558
+ "clip_ratio/high_max": 0.003294841095339507,
1559
+ "clip_ratio/high_mean": 0.0008237102738348767,
1560
+ "clip_ratio/low_mean": 0.00028246818692423403,
1561
+ "clip_ratio/low_min": 0.0,
1562
+ "clip_ratio/region_mean": 0.0011061784534831531,
1563
+ "epoch": 0.64375,
1564
+ "grad_norm": 1.3377746726311037,
1565
+ "kl": 0.020156481070443988,
1566
+ "learning_rate": 2.981758400104028e-07,
1567
+ "loss": 0.00020956956723239273,
1568
+ "step": 103,
1569
+ "step_time": 24.945010003168136
1570
+ },
1571
+ {
1572
+ "clip_ratio/high_max": 0.00440608240023721,
1573
+ "clip_ratio/high_mean": 0.0011015206000593025,
1574
+ "clip_ratio/low_mean": 0.000277089886367321,
1575
+ "clip_ratio/low_min": 0.0,
1576
+ "clip_ratio/region_mean": 0.0013786104900646023,
1577
+ "epoch": 0.65,
1578
+ "grad_norm": 1.886645919015797,
1579
+ "kl": 0.015945701044984162,
1580
+ "learning_rate": 2.8894603252458403e-07,
1581
+ "loss": -4.721151344710961e-05,
1582
+ "step": 104,
1583
+ "step_time": 24.834263660013676
1584
+ },
1585
+ {
1586
+ "clip_ratio/high_max": 0.0,
1587
+ "clip_ratio/high_mean": 0.0,
1588
+ "clip_ratio/low_mean": 0.0,
1589
+ "clip_ratio/low_min": 0.0,
1590
+ "clip_ratio/region_mean": 0.0,
1591
+ "completions/clipped_ratio": 0.203125,
1592
+ "completions/max_length": 2048.0,
1593
+ "completions/mean_length": 794.328125,
1594
+ "completions/min_length": 69.0,
1595
+ "epoch": 0.65625,
1596
+ "frac_reward_zero_std": 0.21875,
1597
+ "grad_norm": 2.906630125740679,
1598
+ "kl": 0.019378585275262594,
1599
+ "learning_rate": 2.7980292422118277e-07,
1600
+ "loss": 0.00019384961342439055,
1601
+ "reward": 0.46875,
1602
+ "reward_std": 0.3524448871612549,
1603
+ "rewards/MajorityAccuracy/mean": 0.46875,
1604
+ "rewards/MajorityAccuracy/std": 0.5,
1605
+ "step": 105,
1606
+ "step_time": 182.74002473335713
1607
+ },
1608
+ {
1609
+ "clip_ratio/high_max": 0.00464864460809622,
1610
+ "clip_ratio/high_mean": 0.0011980600866081659,
1611
+ "clip_ratio/low_mean": 0.0002857408544514328,
1612
+ "clip_ratio/low_min": 0.0,
1613
+ "clip_ratio/region_mean": 0.0014838009701634292,
1614
+ "epoch": 0.6625,
1615
+ "grad_norm": 5.348660964308739,
1616
+ "kl": 0.04366080742329359,
1617
+ "learning_rate": 2.70750271011657e-07,
1618
+ "loss": 0.000708715058863163,
1619
+ "step": 106,
1620
+ "step_time": 24.580459790304303
1621
+ },
1622
+ {
1623
+ "clip_ratio/high_max": 0.0015517349675064906,
1624
+ "clip_ratio/high_mean": 0.00042870347897405736,
1625
+ "clip_ratio/low_mean": 0.00021158602976356633,
1626
+ "clip_ratio/low_min": 0.0,
1627
+ "clip_ratio/region_mean": 0.0006402895087376237,
1628
+ "epoch": 0.66875,
1629
+ "grad_norm": 1.612926768950073,
1630
+ "kl": 0.009279580088332295,
1631
+ "learning_rate": 2.6179179164927754e-07,
1632
+ "loss": 0.00023716760915704072,
1633
+ "step": 107,
1634
+ "step_time": 25.75847982848063
1635
+ },
1636
+ {
1637
+ "clip_ratio/high_max": 0.003422082547331229,
1638
+ "clip_ratio/high_mean": 0.001039439972373657,
1639
+ "clip_ratio/low_mean": 0.0003285885904915631,
1640
+ "clip_ratio/low_min": 0.0,
1641
+ "clip_ratio/region_mean": 0.0013680285483133048,
1642
+ "epoch": 0.675,
1643
+ "grad_norm": 2.8390681534775375,
1644
+ "kl": 0.021288370015099645,
1645
+ "learning_rate": 2.529311662014972e-07,
1646
+ "loss": 0.0006155818700790405,
1647
+ "step": 108,
1648
+ "step_time": 24.10438273055479
1649
+ },
1650
+ {
1651
+ "clip_ratio/high_max": 0.004911001888103783,
1652
+ "clip_ratio/high_mean": 0.0015158808600972407,
1653
+ "clip_ratio/low_mean": 0.0007953805761644617,
1654
+ "clip_ratio/low_min": 0.0,
1655
+ "clip_ratio/region_mean": 0.0023112613998819143,
1656
+ "epoch": 0.68125,
1657
+ "grad_norm": 3.799845195333566,
1658
+ "kl": 0.03941259835846722,
1659
+ "learning_rate": 2.441720345382089e-07,
1660
+ "loss": -5.1648676162585616e-05,
1661
+ "step": 109,
1662
+ "step_time": 22.739543860778213
1663
+ },
1664
+ {
1665
+ "clip_ratio/high_max": 0.0010399125749245286,
1666
+ "clip_ratio/high_mean": 0.00025997814373113215,
1667
+ "clip_ratio/low_mean": 0.000760422226449009,
1668
+ "clip_ratio/low_min": 0.0,
1669
+ "clip_ratio/region_mean": 0.0010204003847320564,
1670
+ "epoch": 0.6875,
1671
+ "grad_norm": 3.425829260950132,
1672
+ "kl": 0.021432430250570178,
1673
+ "learning_rate": 2.355179948365189e-07,
1674
+ "loss": 0.0006575718871317804,
1675
+ "step": 110,
1676
+ "step_time": 23.417079218197614
1677
+ },
1678
+ {
1679
+ "clip_ratio/high_max": 0.004584776877891272,
1680
+ "clip_ratio/high_mean": 0.0018162674532504752,
1681
+ "clip_ratio/low_mean": 0.0006794104556320235,
1682
+ "clip_ratio/low_min": 0.0,
1683
+ "clip_ratio/region_mean": 0.0024956778797786683,
1684
+ "epoch": 0.69375,
1685
+ "grad_norm": 3.7057459321326176,
1686
+ "kl": 0.018441698979586363,
1687
+ "learning_rate": 2.26972602102645e-07,
1688
+ "loss": 1.2700125807896256e-05,
1689
+ "step": 111,
1690
+ "step_time": 24.406328023411334
1691
+ },
1692
+ {
1693
+ "clip_ratio/high_max": 0.0071835165144875646,
1694
+ "clip_ratio/high_mean": 0.002048340582405217,
1695
+ "clip_ratio/low_mean": 0.0003899169896612875,
1696
+ "clip_ratio/low_min": 0.0,
1697
+ "clip_ratio/region_mean": 0.0024382575866184197,
1698
+ "epoch": 0.7,
1699
+ "grad_norm": 2.1697108742361872,
1700
+ "kl": 0.019718975061550736,
1701
+ "learning_rate": 2.1853936671155127e-07,
1702
+ "loss": 0.00043255178024992347,
1703
+ "step": 112,
1704
+ "step_time": 24.947264580521733
1705
+ },
1706
+ {
1707
+ "clip_ratio/high_max": 0.0,
1708
+ "clip_ratio/high_mean": 0.0,
1709
+ "clip_ratio/low_mean": 0.0,
1710
+ "clip_ratio/low_min": 0.0,
1711
+ "clip_ratio/region_mean": 0.0,
1712
+ "completions/clipped_ratio": 0.27734375,
1713
+ "completions/max_length": 2048.0,
1714
+ "completions/mean_length": 1057.3515625,
1715
+ "completions/min_length": 72.0,
1716
+ "epoch": 0.70625,
1717
+ "frac_reward_zero_std": 0.125,
1718
+ "grad_norm": 1.834847385081377,
1719
+ "kl": 0.016988730058073997,
1720
+ "learning_rate": 2.1022175296491512e-07,
1721
+ "loss": 0.0001699887216091156,
1722
+ "reward": 0.39453125,
1723
+ "reward_std": 0.39690107107162476,
1724
+ "rewards/MajorityAccuracy/mean": 0.39453125,
1725
+ "rewards/MajorityAccuracy/std": 0.48970717191696167,
1726
+ "step": 113,
1727
+ "step_time": 187.62890050327405
1728
+ },
1729
+ {
1730
+ "clip_ratio/high_max": 0.001759141421644017,
1731
+ "clip_ratio/high_mean": 0.00061360287872958,
1732
+ "clip_ratio/low_mean": 0.00031236752693075687,
1733
+ "clip_ratio/low_min": 0.0,
1734
+ "clip_ratio/region_mean": 0.0009259703983843792,
1735
+ "epoch": 0.7125,
1736
+ "grad_norm": 2.0213924719836704,
1737
+ "kl": 0.017376792151480913,
1738
+ "learning_rate": 2.0202317766802152e-07,
1739
+ "loss": 0.0002892809279728681,
1740
+ "step": 114,
1741
+ "step_time": 24.988385637756437
1742
+ },
1743
+ {
1744
+ "clip_ratio/high_max": 0.0,
1745
+ "clip_ratio/high_mean": 0.0,
1746
+ "clip_ratio/low_mean": 0.0002791200240608305,
1747
+ "clip_ratio/low_min": 0.0,
1748
+ "clip_ratio/region_mean": 0.0002791200240608305,
1749
+ "epoch": 0.71875,
1750
+ "grad_norm": 0.7921275408906617,
1751
+ "kl": 0.012203714344650507,
1752
+ "learning_rate": 1.9394700872616853e-07,
1753
+ "loss": 0.00018957597785629332,
1754
+ "step": 115,
1755
+ "step_time": 25.44249103870243
1756
+ },
1757
+ {
1758
+ "clip_ratio/high_max": 0.0024992944672703743,
1759
+ "clip_ratio/high_mean": 0.0006895661208545789,
1760
+ "clip_ratio/low_mean": 0.0011220419291930739,
1761
+ "clip_ratio/low_min": 0.0,
1762
+ "clip_ratio/region_mean": 0.001811608046409674,
1763
+ "epoch": 0.725,
1764
+ "grad_norm": 3.4523471680911384,
1765
+ "kl": 0.028104545082896948,
1766
+ "learning_rate": 1.8599656376116024e-07,
1767
+ "loss": 0.0008925870060920715,
1768
+ "step": 116,
1769
+ "step_time": 24.78544593602419
1770
+ },
1771
+ {
1772
+ "clip_ratio/high_max": 0.0019484558288240805,
1773
+ "clip_ratio/high_mean": 0.0005250617359706666,
1774
+ "clip_ratio/low_mean": 0.0011562893923837692,
1775
+ "clip_ratio/low_min": 0.0,
1776
+ "clip_ratio/region_mean": 0.0016813511465443298,
1777
+ "epoch": 0.73125,
1778
+ "grad_norm": 2.7451911195891388,
1779
+ "kl": 0.010697404970414937,
1780
+ "learning_rate": 1.7817510874845582e-07,
1781
+ "loss": 0.0003750985488295555,
1782
+ "step": 117,
1783
+ "step_time": 25.902589215897024
1784
+ },
1785
+ {
1786
+ "clip_ratio/high_max": 0.00874110592121724,
1787
+ "clip_ratio/high_mean": 0.0030371647553693037,
1788
+ "clip_ratio/low_mean": 0.0010490551958355354,
1789
+ "clip_ratio/low_min": 0.0,
1790
+ "clip_ratio/region_mean": 0.004086219938471913,
1791
+ "epoch": 0.7375,
1792
+ "grad_norm": 3.8635631568046636,
1793
+ "kl": 0.020631589693948627,
1794
+ "learning_rate": 1.7048585667553412e-07,
1795
+ "loss": 0.0001955423504114151,
1796
+ "step": 118,
1797
+ "step_time": 24.245086643844843
1798
+ },
1799
+ {
1800
+ "clip_ratio/high_max": 0.007139264867873862,
1801
+ "clip_ratio/high_mean": 0.0024620661642984487,
1802
+ "clip_ratio/low_mean": 0.0015657871299481485,
1803
+ "clip_ratio/low_min": 0.0,
1804
+ "clip_ratio/region_mean": 0.004027853312436491,
1805
+ "epoch": 0.74375,
1806
+ "grad_norm": 5.661842027588935,
1807
+ "kl": 0.055140248499810696,
1808
+ "learning_rate": 1.6293196622202632e-07,
1809
+ "loss": 0.001989663578569889,
1810
+ "step": 119,
1811
+ "step_time": 22.668785023503006
1812
+ },
1813
+ {
1814
+ "clip_ratio/high_max": 0.006877413048641756,
1815
+ "clip_ratio/high_mean": 0.002488244885171298,
1816
+ "clip_ratio/low_mean": 0.0005582967296504648,
1817
+ "clip_ratio/low_min": 0.0,
1818
+ "clip_ratio/region_mean": 0.003046541611183784,
1819
+ "epoch": 0.75,
1820
+ "grad_norm": 6.489454761072265,
1821
+ "kl": 0.027677682461217046,
1822
+ "learning_rate": 1.555165404621567e-07,
1823
+ "loss": 0.0009282324463129044,
1824
+ "step": 120,
1825
+ "step_time": 24.72197053115815
1826
+ },
1827
+ {
1828
+ "clip_ratio/high_max": 0.0,
1829
+ "clip_ratio/high_mean": 0.0,
1830
+ "clip_ratio/low_mean": 0.0,
1831
+ "clip_ratio/low_min": 0.0,
1832
+ "clip_ratio/region_mean": 0.0,
1833
+ "completions/clipped_ratio": 0.14453125,
1834
+ "completions/max_length": 2048.0,
1835
+ "completions/mean_length": 643.7734375,
1836
+ "completions/min_length": 68.0,
1837
+ "epoch": 0.75625,
1838
+ "frac_reward_zero_std": 0.25,
1839
+ "grad_norm": 2.153117878379725,
1840
+ "kl": 0.02426104713231325,
1841
+ "learning_rate": 1.4824262559002592e-07,
1842
+ "loss": 0.00024268688866868615,
1843
+ "reward": 0.421875,
1844
+ "reward_std": 0.32378628849983215,
1845
+ "rewards/MajorityAccuracy/mean": 0.421875,
1846
+ "rewards/MajorityAccuracy/std": 0.49482616782188416,
1847
+ "step": 121,
1848
+ "step_time": 181.66051422199234
1849
+ },
1850
+ {
1851
+ "clip_ratio/high_max": 0.0014186665939632803,
1852
+ "clip_ratio/high_mean": 0.0003897396018146537,
1853
+ "clip_ratio/low_mean": 0.000269338401267305,
1854
+ "clip_ratio/low_min": 0.0,
1855
+ "clip_ratio/region_mean": 0.0006590780067199375,
1856
+ "epoch": 0.7625,
1857
+ "grad_norm": 3.4862998639290095,
1858
+ "kl": 0.025164034217596054,
1859
+ "learning_rate": 1.4111320966826057e-07,
1860
+ "loss": 0.000420544296503067,
1861
+ "step": 122,
1862
+ "step_time": 24.6387906097807
1863
+ },
1864
+ {
1865
+ "clip_ratio/high_max": 0.002989096159581095,
1866
+ "clip_ratio/high_mean": 0.0010213146888418123,
1867
+ "clip_ratio/low_mean": 0.0021447987055580597,
1868
+ "clip_ratio/low_min": 0.0,
1869
+ "clip_ratio/region_mean": 0.003166113398037851,
1870
+ "epoch": 0.76875,
1871
+ "grad_norm": 2.788544083205481,
1872
+ "kl": 0.038733203429728746,
1873
+ "learning_rate": 1.3413122140054217e-07,
1874
+ "loss": 0.0002301940694451332,
1875
+ "step": 123,
1876
+ "step_time": 24.108364638872445
1877
+ },
1878
+ {
1879
+ "clip_ratio/high_max": 0.003125094808638096,
1880
+ "clip_ratio/high_mean": 0.0010724372987169772,
1881
+ "clip_ratio/low_mean": 0.00011407372949179262,
1882
+ "clip_ratio/low_min": 0.0,
1883
+ "clip_ratio/region_mean": 0.0011865110282087699,
1884
+ "epoch": 0.775,
1885
+ "grad_norm": 2.8826082693472017,
1886
+ "kl": 0.030851490097120404,
1887
+ "learning_rate": 1.272995289285202e-07,
1888
+ "loss": 0.00016912080172915012,
1889
+ "step": 124,
1890
+ "step_time": 25.265596106182784
1891
+ },
1892
+ {
1893
+ "clip_ratio/high_max": 0.006712413392961025,
1894
+ "clip_ratio/high_mean": 0.0018669251003302634,
1895
+ "clip_ratio/low_mean": 0.00099228008184582,
1896
+ "clip_ratio/low_min": 0.0,
1897
+ "clip_ratio/region_mean": 0.0028592052112799138,
1898
+ "epoch": 0.78125,
1899
+ "grad_norm": 4.5289885911803225,
1900
+ "kl": 0.029157961951568723,
1901
+ "learning_rate": 1.2062093865360457e-07,
1902
+ "loss": 0.0007396843284368515,
1903
+ "step": 125,
1904
+ "step_time": 24.873047617264092
1905
+ },
1906
+ {
1907
+ "clip_ratio/high_max": 0.007262448139954358,
1908
+ "clip_ratio/high_mean": 0.002312089258339256,
1909
+ "clip_ratio/low_mean": 0.001343338093647617,
1910
+ "clip_ratio/low_min": 0.0,
1911
+ "clip_ratio/region_mean": 0.0036554273901856504,
1912
+ "epoch": 0.7875,
1913
+ "grad_norm": 5.384350891903328,
1914
+ "kl": 0.04755130363628268,
1915
+ "learning_rate": 1.1409819408411897e-07,
1916
+ "loss": 0.0014473330229520798,
1917
+ "step": 126,
1918
+ "step_time": 22.751093410421163
1919
+ },
1920
+ {
1921
+ "clip_ratio/high_max": 0.0006389666814357042,
1922
+ "clip_ratio/high_mean": 0.00015974167035892606,
1923
+ "clip_ratio/low_mean": 0.00037955999141559005,
1924
+ "clip_ratio/low_min": 0.0,
1925
+ "clip_ratio/region_mean": 0.0005393016581365373,
1926
+ "epoch": 0.79375,
1927
+ "grad_norm": 1.303005814177819,
1928
+ "kl": 0.02461914694868028,
1929
+ "learning_rate": 1.0773397470829143e-07,
1930
+ "loss": 0.00018015191017184407,
1931
+ "step": 127,
1932
+ "step_time": 24.703044613823295
1933
+ },
1934
+ {
1935
+ "clip_ratio/high_max": 0.001717350780381821,
1936
+ "clip_ratio/high_mean": 0.0005060248040535953,
1937
+ "clip_ratio/low_mean": 0.000754391381633468,
1938
+ "clip_ratio/low_min": 0.0,
1939
+ "clip_ratio/region_mean": 0.0012604162002389785,
1940
+ "epoch": 0.8,
1941
+ "grad_norm": 6.139433435238711,
1942
+ "kl": 0.02554444782435894,
1943
+ "learning_rate": 1.0153089489354256e-07,
1944
+ "loss": 0.0012572528794407845,
1945
+ "step": 128,
1946
+ "step_time": 23.53158607147634
1947
+ },
1948
+ {
1949
+ "clip_ratio/high_max": 0.0,
1950
+ "clip_ratio/high_mean": 0.0,
1951
+ "clip_ratio/low_mean": 0.0,
1952
+ "clip_ratio/low_min": 0.0,
1953
+ "clip_ratio/region_mean": 0.0,
1954
+ "completions/clipped_ratio": 0.109375,
1955
+ "completions/max_length": 2048.0,
1956
+ "completions/mean_length": 701.77734375,
1957
+ "completions/min_length": 96.0,
1958
+ "epoch": 0.80625,
1959
+ "frac_reward_zero_std": 0.28125,
1960
+ "grad_norm": 1.4942059857380567,
1961
+ "kl": 0.018515312229283154,
1962
+ "learning_rate": 9.549150281252632e-08,
1963
+ "loss": 0.00018516277486924082,
1964
+ "reward": 0.43359375,
1965
+ "reward_std": 0.3257533311843872,
1966
+ "rewards/MajorityAccuracy/mean": 0.43359375,
1967
+ "rewards/MajorityAccuracy/std": 0.4965413510799408,
1968
+ "step": 129,
1969
+ "step_time": 181.47640796471387
1970
+ },
1971
+ {
1972
+ "clip_ratio/high_max": 0.0017779997433535755,
1973
+ "clip_ratio/high_mean": 0.00044449993583839387,
1974
+ "clip_ratio/low_mean": 0.0003385974487173371,
1975
+ "clip_ratio/low_min": 0.0,
1976
+ "clip_ratio/region_mean": 0.000783097384555731,
1977
+ "epoch": 0.8125,
1978
+ "grad_norm": 2.4957350519839077,
1979
+ "kl": 0.02508621127344668,
1980
+ "learning_rate": 8.961827939636196e-08,
1981
+ "loss": 0.0002633974945638329,
1982
+ "step": 130,
1983
+ "step_time": 22.77932652970776
1984
+ },
1985
+ {
1986
+ "clip_ratio/high_max": 0.0027794887428171933,
1987
+ "clip_ratio/high_mean": 0.0006948721857042983,
1988
+ "clip_ratio/low_mean": 0.0003098918023169972,
1989
+ "clip_ratio/low_min": 0.0,
1990
+ "clip_ratio/region_mean": 0.0010047639880212955,
1991
+ "epoch": 0.81875,
1992
+ "grad_norm": 4.000053145281806,
1993
+ "kl": 0.016045384691096842,
1994
+ "learning_rate": 8.391363731548811e-08,
1995
+ "loss": 0.0005064585711807013,
1996
+ "step": 131,
1997
+ "step_time": 24.520836324431002
1998
+ },
1999
+ {
2000
+ "clip_ratio/high_max": 0.0027434531511971727,
2001
+ "clip_ratio/high_mean": 0.0009057832248799969,
2002
+ "clip_ratio/low_mean": 0.0013701298339583445,
2003
+ "clip_ratio/low_min": 0.00015470296784769744,
2004
+ "clip_ratio/region_mean": 0.0022759130224585533,
2005
+ "epoch": 0.825,
2006
+ "grad_norm": 3.228197850167453,
2007
+ "kl": 0.031013467349112034,
2008
+ "learning_rate": 7.837991998855897e-08,
2009
+ "loss": 0.0003987615928053856,
2010
+ "step": 132,
2011
+ "step_time": 24.35424795234576
2012
+ },
2013
+ {
2014
+ "clip_ratio/high_max": 0.002018849627347663,
2015
+ "clip_ratio/high_mean": 0.0005448299307317939,
2016
+ "clip_ratio/low_mean": 0.000152587890625,
2017
+ "clip_ratio/low_min": 0.0,
2018
+ "clip_ratio/region_mean": 0.0006974178177188151,
2019
+ "epoch": 0.83125,
2020
+ "grad_norm": 2.5302613269570164,
2021
+ "kl": 0.02394848153926432,
2022
+ "learning_rate": 7.301940061978722e-08,
2023
+ "loss": 0.0003671912127174437,
2024
+ "step": 133,
2025
+ "step_time": 24.812364160548896
2026
+ },
2027
+ {
2028
+ "clip_ratio/high_max": 0.0030411765837925486,
2029
+ "clip_ratio/high_mean": 0.0008605753155279672,
2030
+ "clip_ratio/low_mean": 0.0005264460978651186,
2031
+ "clip_ratio/low_min": 0.0,
2032
+ "clip_ratio/region_mean": 0.0013870214024791494,
2033
+ "epoch": 0.8375,
2034
+ "grad_norm": 2.4399397608600704,
2035
+ "kl": 0.011691318126395345,
2036
+ "learning_rate": 6.783428126513125e-08,
2037
+ "loss": 0.00035769399255514145,
2038
+ "step": 134,
2039
+ "step_time": 23.85107445018366
2040
+ },
2041
+ {
2042
+ "clip_ratio/high_max": 0.002914530909038149,
2043
+ "clip_ratio/high_mean": 0.0007818695266905706,
2044
+ "clip_ratio/low_mean": 0.0006749165913788602,
2045
+ "clip_ratio/low_min": 0.0,
2046
+ "clip_ratio/region_mean": 0.0014567861035175156,
2047
+ "epoch": 0.84375,
2048
+ "grad_norm": 3.1701048319834997,
2049
+ "kl": 0.02692955150268972,
2050
+ "learning_rate": 6.282669192770895e-08,
2051
+ "loss": 0.0006305094575509429,
2052
+ "step": 135,
2053
+ "step_time": 25.043582652695477
2054
+ },
2055
+ {
2056
+ "clip_ratio/high_max": 0.003956293890951201,
2057
+ "clip_ratio/high_mean": 0.0009890734727378003,
2058
+ "clip_ratio/low_mean": 0.0017431625819881447,
2059
+ "clip_ratio/low_min": 0.0,
2060
+ "clip_ratio/region_mean": 0.0027322359892423265,
2061
+ "epoch": 0.85,
2062
+ "grad_norm": 6.309787663218345,
2063
+ "kl": 0.01816174457781017,
2064
+ "learning_rate": 5.799868968281074e-08,
2065
+ "loss": 0.0006853595259599388,
2066
+ "step": 136,
2067
+ "step_time": 24.226780608762056
2068
+ },
2069
+ {
2070
+ "clip_ratio/high_max": 0.0,
2071
+ "clip_ratio/high_mean": 0.0,
2072
+ "clip_ratio/low_mean": 0.0,
2073
+ "clip_ratio/low_min": 0.0,
2074
+ "clip_ratio/region_mean": 0.0,
2075
+ "completions/clipped_ratio": 0.25,
2076
+ "completions/max_length": 2048.0,
2077
+ "completions/mean_length": 874.69921875,
2078
+ "completions/min_length": 80.0,
2079
+ "epoch": 0.85625,
2080
+ "frac_reward_zero_std": 0.3125,
2081
+ "grad_norm": 1.2901454877093643,
2082
+ "kl": 0.01794887939468026,
2083
+ "learning_rate": 5.335225783287051e-08,
2084
+ "loss": 0.00017949219909496605,
2085
+ "reward": 0.3359375,
2086
+ "reward_std": 0.304455041885376,
2087
+ "rewards/MajorityAccuracy/mean": 0.3359375,
2088
+ "rewards/MajorityAccuracy/std": 0.4732423424720764,
2089
+ "step": 137,
2090
+ "step_time": 184.06394059257582
2091
+ },
2092
+ {
2093
+ "clip_ratio/high_max": 0.003017716502654366,
2094
+ "clip_ratio/high_mean": 0.0008629672629467677,
2095
+ "clip_ratio/low_mean": 0.002210470222053118,
2096
+ "clip_ratio/low_min": 0.0,
2097
+ "clip_ratio/region_mean": 0.003073437495913822,
2098
+ "epoch": 0.8625,
2099
+ "grad_norm": 4.654618457000781,
2100
+ "kl": 0.01841490692459047,
2101
+ "learning_rate": 4.888930509274125e-08,
2102
+ "loss": -6.196461617946625e-05,
2103
+ "step": 138,
2104
+ "step_time": 24.529710309114307
2105
+ },
2106
+ {
2107
+ "clip_ratio/high_max": 0.0022114876483101398,
2108
+ "clip_ratio/high_mean": 0.0006933213517186232,
2109
+ "clip_ratio/low_mean": 0.00017026290515786968,
2110
+ "clip_ratio/low_min": 0.0,
2111
+ "clip_ratio/region_mean": 0.0008635842605144717,
2112
+ "epoch": 0.86875,
2113
+ "grad_norm": 2.6834222200041458,
2114
+ "kl": 0.027394989039748907,
2115
+ "learning_rate": 4.4611664805611794e-08,
2116
+ "loss": 6.076198042137548e-05,
2117
+ "step": 139,
2118
+ "step_time": 24.255662749987096
2119
+ },
2120
+ {
2121
+ "clip_ratio/high_max": 0.0012455770338419825,
2122
+ "clip_ratio/high_mean": 0.0003113942584604956,
2123
+ "clip_ratio/low_mean": 0.00034186382617917843,
2124
+ "clip_ratio/low_min": 0.0,
2125
+ "clip_ratio/region_mean": 0.000653258084639674,
2126
+ "epoch": 0.875,
2127
+ "grad_norm": 2.1891985669139236,
2128
+ "kl": 0.019985553110018373,
2129
+ "learning_rate": 4.0521094189884696e-08,
2130
+ "loss": 0.00022457289742305875,
2131
+ "step": 140,
2132
+ "step_time": 24.38839391246438
2133
+ },
2134
+ {
2135
+ "clip_ratio/high_max": 0.0022284688893705606,
2136
+ "clip_ratio/high_mean": 0.0005571172223426402,
2137
+ "clip_ratio/low_mean": 0.0010212962297373451,
2138
+ "clip_ratio/low_min": 0.0,
2139
+ "clip_ratio/region_mean": 0.0015784134811838157,
2140
+ "epoch": 0.88125,
2141
+ "grad_norm": 3.128504290514939,
2142
+ "kl": 0.023765610996633768,
2143
+ "learning_rate": 3.6619273617325695e-08,
2144
+ "loss": 0.0007229488110169768,
2145
+ "step": 141,
2146
+ "step_time": 25.14083173358813
2147
+ },
2148
+ {
2149
+ "clip_ratio/high_max": 0.0004649078255170025,
2150
+ "clip_ratio/high_mean": 0.00011622695637925062,
2151
+ "clip_ratio/low_mean": 0.00012180470730527304,
2152
+ "clip_ratio/low_min": 0.0,
2153
+ "clip_ratio/region_mean": 0.00023803166368452366,
2154
+ "epoch": 0.8875,
2155
+ "grad_norm": 1.4746430737094118,
2156
+ "kl": 0.026893890695646405,
2157
+ "learning_rate": 3.2907805922781476e-08,
2158
+ "loss": 0.0005526706809177995,
2159
+ "step": 142,
2160
+ "step_time": 25.09106065193191
2161
+ },
2162
+ {
2163
+ "clip_ratio/high_max": 0.005163752241060138,
2164
+ "clip_ratio/high_mean": 0.0013843890192219988,
2165
+ "clip_ratio/low_mean": 0.0005321941134752706,
2166
+ "clip_ratio/low_min": 0.0,
2167
+ "clip_ratio/region_mean": 0.0019165831326972693,
2168
+ "epoch": 0.89375,
2169
+ "grad_norm": 4.796116164863861,
2170
+ "kl": 0.028787377988919616,
2171
+ "learning_rate": 2.9388215745748345e-08,
2172
+ "loss": 0.00023962464183568954,
2173
+ "step": 143,
2174
+ "step_time": 24.72295349324122
2175
+ },
2176
+ {
2177
+ "clip_ratio/high_max": 0.006954727286938578,
2178
+ "clip_ratio/high_mean": 0.002303481596754864,
2179
+ "clip_ratio/low_mean": 0.0018399724358459935,
2180
+ "clip_ratio/low_min": 0.0,
2181
+ "clip_ratio/region_mean": 0.004143454018048942,
2182
+ "epoch": 0.9,
2183
+ "grad_norm": 5.135254383250401,
2184
+ "kl": 0.03203576221130788,
2185
+ "learning_rate": 2.6061948904063658e-08,
2186
+ "loss": 0.0010435234289616346,
2187
+ "step": 144,
2188
+ "step_time": 22.3231020597741
2189
+ },
2190
+ {
2191
+ "clip_ratio/high_max": 0.0,
2192
+ "clip_ratio/high_mean": 0.0,
2193
+ "clip_ratio/low_mean": 0.0,
2194
+ "clip_ratio/low_min": 0.0,
2195
+ "clip_ratio/region_mean": 0.0,
2196
+ "completions/clipped_ratio": 0.1953125,
2197
+ "completions/max_length": 2048.0,
2198
+ "completions/mean_length": 823.125,
2199
+ "completions/min_length": 65.0,
2200
+ "epoch": 0.90625,
2201
+ "frac_reward_zero_std": 0.21875,
2202
+ "grad_norm": 2.12882005785719,
2203
+ "kl": 0.03510537534020841,
2204
+ "learning_rate": 2.293037179997559e-08,
2205
+ "loss": 0.0003509829693939537,
2206
+ "reward": 0.359375,
2207
+ "reward_std": 0.3353603482246399,
2208
+ "rewards/MajorityAccuracy/mean": 0.359375,
2209
+ "rewards/MajorityAccuracy/std": 0.4807571768760681,
2210
+ "step": 145,
2211
+ "step_time": 185.1893007569015
2212
+ },
2213
+ {
2214
+ "clip_ratio/high_max": 0.007391202845610678,
2215
+ "clip_ratio/high_mean": 0.00206038577016443,
2216
+ "clip_ratio/low_mean": 0.0014160471437207889,
2217
+ "clip_ratio/low_min": 0.0,
2218
+ "clip_ratio/region_mean": 0.0034764328447636217,
2219
+ "epoch": 0.9125,
2220
+ "grad_norm": 7.773241420145666,
2221
+ "kl": 0.013852762524038553,
2222
+ "learning_rate": 1.9994770858837107e-08,
2223
+ "loss": -4.9904920160770416e-05,
2224
+ "step": 146,
2225
+ "step_time": 25.05885120620951
2226
+ },
2227
+ {
2228
+ "clip_ratio/high_max": 0.0,
2229
+ "clip_ratio/high_mean": 0.0,
2230
+ "clip_ratio/low_mean": 0.0002751157298916951,
2231
+ "clip_ratio/low_min": 0.0,
2232
+ "clip_ratio/region_mean": 0.0002751157298916951,
2233
+ "epoch": 0.91875,
2234
+ "grad_norm": 2.0342520585043364,
2235
+ "kl": 0.023822985123842955,
2236
+ "learning_rate": 1.725635200065323e-08,
2237
+ "loss": 0.00024401575501542538,
2238
+ "step": 147,
2239
+ "step_time": 24.7170759155415
2240
+ },
2241
+ {
2242
+ "clip_ratio/high_max": 0.002574237121734768,
2243
+ "clip_ratio/high_mean": 0.000643559280433692,
2244
+ "clip_ratio/low_mean": 0.00022307676590571646,
2245
+ "clip_ratio/low_min": 0.0,
2246
+ "clip_ratio/region_mean": 0.0008666360445204191,
2247
+ "epoch": 0.925,
2248
+ "grad_norm": 2.1686180719510992,
2249
+ "kl": 0.016511363559402525,
2250
+ "learning_rate": 1.4716240144699187e-08,
2251
+ "loss": 0.0003834535600617528,
2252
+ "step": 148,
2253
+ "step_time": 24.701466805767268
2254
+ },
2255
+ {
2256
+ "clip_ratio/high_max": 0.0034430744708515704,
2257
+ "clip_ratio/high_mean": 0.0012442041916074231,
2258
+ "clip_ratio/low_mean": 0.0011874331466970034,
2259
+ "clip_ratio/low_min": 0.0,
2260
+ "clip_ratio/region_mean": 0.0024316373383044265,
2261
+ "epoch": 0.93125,
2262
+ "grad_norm": 5.458512217948682,
2263
+ "kl": 0.016237835749052465,
2264
+ "learning_rate": 1.2375478747413015e-08,
2265
+ "loss": 0.0006329668685793877,
2266
+ "step": 149,
2267
+ "step_time": 24.63124997774139
2268
+ },
2269
+ {
2270
+ "clip_ratio/high_max": 0.0019827992655336857,
2271
+ "clip_ratio/high_mean": 0.0006071742391213775,
2272
+ "clip_ratio/low_mean": 0.0005518667458090931,
2273
+ "clip_ratio/low_min": 0.0,
2274
+ "clip_ratio/region_mean": 0.0011590409994823858,
2275
+ "epoch": 0.9375,
2276
+ "grad_norm": 13.041952384889175,
2277
+ "kl": 0.014135191100649536,
2278
+ "learning_rate": 1.0235029373752757e-08,
2279
+ "loss": 0.0004027679096907377,
2280
+ "step": 150,
2281
+ "step_time": 24.85483159357682
2282
+ },
2283
+ {
2284
+ "clip_ratio/high_max": 0.0061735211638733745,
2285
+ "clip_ratio/high_mean": 0.0019042672065552324,
2286
+ "clip_ratio/low_mean": 0.0001279516436625272,
2287
+ "clip_ratio/low_min": 0.0,
2288
+ "clip_ratio/region_mean": 0.0020322188502177596,
2289
+ "epoch": 0.94375,
2290
+ "grad_norm": 7.225858388271463,
2291
+ "kl": 0.03300457680597901,
2292
+ "learning_rate": 8.295771302193721e-09,
2293
+ "loss": 0.0001865895465016365,
2294
+ "step": 151,
2295
+ "step_time": 23.459914714097977
2296
+ },
2297
+ {
2298
+ "clip_ratio/high_max": 0.003357184585183859,
2299
+ "clip_ratio/high_mean": 0.0010640114269335754,
2300
+ "clip_ratio/low_mean": 0.0008358918421436101,
2301
+ "clip_ratio/low_min": 0.0,
2302
+ "clip_ratio/region_mean": 0.0018999032690771855,
2303
+ "epoch": 0.95,
2304
+ "grad_norm": 2.021704458877521,
2305
+ "kl": 0.026009109569713473,
2306
+ "learning_rate": 6.558501163527963e-09,
2307
+ "loss": 5.353331653168425e-05,
2308
+ "step": 152,
2309
+ "step_time": 23.422796375583857
2310
+ },
2311
+ {
2312
+ "clip_ratio/high_max": 0.0,
2313
+ "clip_ratio/high_mean": 0.0,
2314
+ "clip_ratio/low_mean": 0.0,
2315
+ "clip_ratio/low_min": 0.0,
2316
+ "clip_ratio/region_mean": 0.0,
2317
+ "completions/clipped_ratio": 0.1015625,
2318
+ "completions/max_length": 2048.0,
2319
+ "completions/mean_length": 630.85546875,
2320
+ "completions/min_length": 75.0,
2321
+ "epoch": 0.95625,
2322
+ "frac_reward_zero_std": 0.375,
2323
+ "grad_norm": 2.1575015378414255,
2324
+ "kl": 0.022879542550072074,
2325
+ "learning_rate": 5.023932613615445e-09,
2326
+ "loss": 0.00022884564532432705,
2327
+ "reward": 0.5234375,
2328
+ "reward_std": 0.2885436713695526,
2329
+ "rewards/MajorityAccuracy/mean": 0.5234375,
2330
+ "rewards/MajorityAccuracy/std": 0.5004287362098694,
2331
+ "step": 153,
2332
+ "step_time": 177.1041503874585
2333
+ },
2334
+ {
2335
+ "clip_ratio/high_max": 0.0015324694541050121,
2336
+ "clip_ratio/high_mean": 0.00038311736352625303,
2337
+ "clip_ratio/low_mean": 0.0010349983058404177,
2338
+ "clip_ratio/low_min": 0.0,
2339
+ "clip_ratio/region_mean": 0.0014181156584527344,
2340
+ "epoch": 0.9625,
2341
+ "grad_norm": 2.1389403218819143,
2342
+ "kl": 0.016948901815339923,
2343
+ "learning_rate": 3.6926960402202666e-09,
2344
+ "loss": -0.00019742324366234243,
2345
+ "step": 154,
2346
+ "step_time": 24.617619512602687
2347
+ },
2348
+ {
2349
+ "clip_ratio/high_max": 0.0028427573561202735,
2350
+ "clip_ratio/high_mean": 0.0007106893390300684,
2351
+ "clip_ratio/low_mean": 0.00016711230273358524,
2352
+ "clip_ratio/low_min": 0.0,
2353
+ "clip_ratio/region_mean": 0.0008778016417636536,
2354
+ "epoch": 0.96875,
2355
+ "grad_norm": 3.2642420182436145,
2356
+ "kl": 0.02572147431783378,
2357
+ "learning_rate": 2.5653383040524224e-09,
2358
+ "loss": 5.610534572042525e-06,
2359
+ "step": 155,
2360
+ "step_time": 25.079640217125416
2361
+ },
2362
+ {
2363
+ "clip_ratio/high_max": 0.0047249751223716885,
2364
+ "clip_ratio/high_mean": 0.0014261909091146663,
2365
+ "clip_ratio/low_mean": 0.0004318634746596217,
2366
+ "clip_ratio/low_min": 0.0,
2367
+ "clip_ratio/region_mean": 0.0018580543764983304,
2368
+ "epoch": 0.975,
2369
+ "grad_norm": 4.018461321316175,
2370
+ "kl": 0.03214474464766681,
2371
+ "learning_rate": 1.642322514122385e-09,
2372
+ "loss": 0.00011714361608028412,
2373
+ "step": 156,
2374
+ "step_time": 24.54469154914841
2375
+ },
2376
+ {
2377
+ "clip_ratio/high_max": 0.001125379785662517,
2378
+ "clip_ratio/high_mean": 0.0003460447405814193,
2379
+ "clip_ratio/low_mean": 0.0002486233825038653,
2380
+ "clip_ratio/low_min": 0.0,
2381
+ "clip_ratio/region_mean": 0.0005946681230852846,
2382
+ "epoch": 0.98125,
2383
+ "grad_norm": 2.0285181166297535,
2384
+ "kl": 0.017363176913931966,
2385
+ "learning_rate": 9.240278374995636e-10,
2386
+ "loss": 0.0001132190300268121,
2387
+ "step": 157,
2388
+ "step_time": 23.92594990041107
2389
+ },
2390
+ {
2391
+ "clip_ratio/high_max": 0.005561994039453566,
2392
+ "clip_ratio/high_mean": 0.0019233944040024653,
2393
+ "clip_ratio/low_mean": 0.0004133894581173081,
2394
+ "clip_ratio/low_min": 0.0,
2395
+ "clip_ratio/region_mean": 0.0023367838584817946,
2396
+ "epoch": 0.9875,
2397
+ "grad_norm": 3.779771614134317,
2398
+ "kl": 0.03647417528554797,
2399
+ "learning_rate": 4.1074934355384006e-10,
2400
+ "loss": -0.00015152634296100587,
2401
+ "step": 158,
2402
+ "step_time": 23.600642101839185
2403
+ },
2404
+ {
2405
+ "clip_ratio/high_max": 0.0009575065632816404,
2406
+ "clip_ratio/high_mean": 0.0002393766408204101,
2407
+ "clip_ratio/low_mean": 0.00011665776764857583,
2408
+ "clip_ratio/low_min": 0.0,
2409
+ "clip_ratio/region_mean": 0.00035603440846898593,
2410
+ "epoch": 0.99375,
2411
+ "grad_norm": 1.0166856894098095,
2412
+ "kl": 0.02641974319703877,
2413
+ "learning_rate": 1.0269788274358537e-10,
2414
+ "loss": 0.0001666850585024804,
2415
+ "step": 159,
2416
+ "step_time": 24.56408547470346
2417
+ },
2418
+ {
2419
+ "clip_ratio/high_max": 0.004306247108615935,
2420
+ "clip_ratio/high_mean": 0.0011658474686555564,
2421
+ "clip_ratio/low_mean": 0.0005622100288746879,
2422
+ "clip_ratio/low_min": 0.0,
2423
+ "clip_ratio/region_mean": 0.0017280574975302443,
2424
+ "epoch": 1.0,
2425
+ "grad_norm": 2.7279545987487794,
2426
+ "kl": 0.028987658442929387,
2427
+ "learning_rate": 0.0,
2428
+ "loss": 0.00018614777945913374,
2429
+ "step": 160,
2430
+ "step_time": 23.525434003211558
2431
+ }
2432
+ ],
2433
+ "logging_steps": 1,
2434
+ "max_steps": 160,
2435
+ "num_input_tokens_seen": 0,
2436
+ "num_train_epochs": 1,
2437
+ "save_steps": 80,
2438
+ "stateful_callbacks": {
2439
+ "TrainerControl": {
2440
+ "args": {
2441
+ "should_epoch_stop": false,
2442
+ "should_evaluate": false,
2443
+ "should_log": false,
2444
+ "should_save": true,
2445
+ "should_training_stop": true
2446
+ },
2447
+ "attributes": {}
2448
+ }
2449
+ },
2450
+ "total_flos": 0.0,
2451
+ "train_batch_size": 1,
2452
+ "trial_name": null,
2453
+ "trial_params": null
2454
+ }