AdithyaSK commited on
Commit
6d866ad
·
verified ·
1 Parent(s): 58d5982

Add files using upload-large-folder tool

Browse files
Files changed (30) hide show
  1. .gitattributes +2 -0
  2. Llama-3.2-3B-GRPO-Indic-v1/checkpoint-100/config.json +40 -0
  3. Llama-3.2-3B-GRPO-Indic-v1/checkpoint-100/generation_config.json +12 -0
  4. Llama-3.2-3B-GRPO-Indic-v1/checkpoint-100/model-00001-of-00002.safetensors +3 -0
  5. Llama-3.2-3B-GRPO-Indic-v1/checkpoint-100/model-00002-of-00002.safetensors +3 -0
  6. Llama-3.2-3B-GRPO-Indic-v1/checkpoint-100/model.safetensors.index.json +261 -0
  7. Llama-3.2-3B-GRPO-Indic-v1/checkpoint-100/optimizer.pt +3 -0
  8. Llama-3.2-3B-GRPO-Indic-v1/checkpoint-100/rng_state_0.pth +3 -0
  9. Llama-3.2-3B-GRPO-Indic-v1/checkpoint-100/rng_state_1.pth +3 -0
  10. Llama-3.2-3B-GRPO-Indic-v1/checkpoint-100/scheduler.pt +3 -0
  11. Llama-3.2-3B-GRPO-Indic-v1/checkpoint-100/special_tokens_map.json +17 -0
  12. Llama-3.2-3B-GRPO-Indic-v1/checkpoint-100/tokenizer.json +3 -0
  13. Llama-3.2-3B-GRPO-Indic-v1/checkpoint-100/tokenizer_config.json +2064 -0
  14. Llama-3.2-3B-GRPO-Indic-v1/checkpoint-100/trainer_state.json +1733 -0
  15. Llama-3.2-3B-GRPO-Indic-v1/checkpoint-100/training_args.bin +3 -0
  16. Qwen2.5-1.5B-GRPO-Indic-v1/checkpoint-100/added_tokens.json +24 -0
  17. Qwen2.5-1.5B-GRPO-Indic-v1/checkpoint-100/config.json +29 -0
  18. Qwen2.5-1.5B-GRPO-Indic-v1/checkpoint-100/generation_config.json +14 -0
  19. Qwen2.5-1.5B-GRPO-Indic-v1/checkpoint-100/merges.txt +0 -0
  20. Qwen2.5-1.5B-GRPO-Indic-v1/checkpoint-100/model.safetensors +3 -0
  21. Qwen2.5-1.5B-GRPO-Indic-v1/checkpoint-100/optimizer.pt +3 -0
  22. Qwen2.5-1.5B-GRPO-Indic-v1/checkpoint-100/rng_state_0.pth +3 -0
  23. Qwen2.5-1.5B-GRPO-Indic-v1/checkpoint-100/rng_state_1.pth +3 -0
  24. Qwen2.5-1.5B-GRPO-Indic-v1/checkpoint-100/scheduler.pt +3 -0
  25. Qwen2.5-1.5B-GRPO-Indic-v1/checkpoint-100/special_tokens_map.json +25 -0
  26. Qwen2.5-1.5B-GRPO-Indic-v1/checkpoint-100/tokenizer.json +3 -0
  27. Qwen2.5-1.5B-GRPO-Indic-v1/checkpoint-100/tokenizer_config.json +208 -0
  28. Qwen2.5-1.5B-GRPO-Indic-v1/checkpoint-100/trainer_state.json +1733 -0
  29. Qwen2.5-1.5B-GRPO-Indic-v1/checkpoint-100/training_args.bin +3 -0
  30. Qwen2.5-1.5B-GRPO-Indic-v1/checkpoint-100/vocab.json +0 -0
.gitattributes CHANGED
@@ -73,3 +73,5 @@ Qwen-0.5B-GRPO-Code-vllm-base/checkpoint-200/tokenizer.json filter=lfs diff=lfs
73
  Qwen-0.5B-GRPO-Code-vllm-base/checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
74
  Qwen-0.5B-GRPO-Code-vllm-base/checkpoint-600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
75
  Qwen-0.5B-GRPO-Code-vllm-base/checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
73
  Qwen-0.5B-GRPO-Code-vllm-base/checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
74
  Qwen-0.5B-GRPO-Code-vllm-base/checkpoint-600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
75
  Qwen-0.5B-GRPO-Code-vllm-base/checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
76
+ Llama-3.2-3B-GRPO-Indic-v1/checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
77
+ Qwen2.5-1.5B-GRPO-Indic-v1/checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
Llama-3.2-3B-GRPO-Indic-v1/checkpoint-100/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Llama-3.2-3B-Instruct",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": [
10
+ 128001,
11
+ 128008,
12
+ 128009
13
+ ],
14
+ "head_dim": 128,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 3072,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 8192,
19
+ "max_position_embeddings": 131072,
20
+ "mlp_bias": false,
21
+ "model_type": "llama",
22
+ "num_attention_heads": 24,
23
+ "num_hidden_layers": 28,
24
+ "num_key_value_heads": 8,
25
+ "pretraining_tp": 1,
26
+ "rms_norm_eps": 1e-05,
27
+ "rope_scaling": {
28
+ "factor": 32.0,
29
+ "high_freq_factor": 4.0,
30
+ "low_freq_factor": 1.0,
31
+ "original_max_position_embeddings": 8192,
32
+ "rope_type": "llama3"
33
+ },
34
+ "rope_theta": 500000.0,
35
+ "tie_word_embeddings": true,
36
+ "torch_dtype": "bfloat16",
37
+ "transformers_version": "4.48.2",
38
+ "use_cache": true,
39
+ "vocab_size": 128256
40
+ }
Llama-3.2-3B-GRPO-Indic-v1/checkpoint-100/generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.48.2"
12
+ }
Llama-3.2-3B-GRPO-Indic-v1/checkpoint-100/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b74ec740338477a3324525e285ae1580c717c95e6dab6e027a2880c1d127b3c
3
+ size 4965799096
Llama-3.2-3B-GRPO-Indic-v1/checkpoint-100/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:039667c2968d2a657e58b4e3f90a510a34f1c2fe43a0e9bcd04f66aaed8acbc3
3
+ size 1459729952
Llama-3.2-3B-GRPO-Indic-v1/checkpoint-100/model.safetensors.index.json ADDED
@@ -0,0 +1,261 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 6425499648
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
90
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
124
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
125
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
126
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
127
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
129
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
130
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
134
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
135
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
136
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
137
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
138
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
139
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
140
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
141
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
142
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
143
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
144
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
145
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
146
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
147
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
148
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
149
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
150
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
151
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
152
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
153
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
154
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
155
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
156
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
157
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
158
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
159
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
160
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
161
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
162
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
163
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
164
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
165
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
166
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
167
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
168
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
169
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
170
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
171
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
172
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
173
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
174
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
175
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
176
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
177
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
178
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
179
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
180
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
181
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
182
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
183
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
184
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
185
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
186
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
187
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
188
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
189
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
190
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
191
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
192
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
193
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
194
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
195
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
196
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
197
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
198
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
199
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
200
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
201
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
202
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
203
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
204
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
205
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
206
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
207
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
208
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
209
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
210
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
211
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
212
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
213
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
214
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
215
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
216
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
217
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
218
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
219
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
220
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
221
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
222
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
223
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
224
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
225
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
226
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
227
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
228
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
229
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
230
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
231
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
232
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
233
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
234
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
235
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
236
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
237
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
238
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
239
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
240
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
241
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
242
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
243
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
244
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
245
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
246
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
247
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
248
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
249
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
250
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
251
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
252
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
253
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
254
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
255
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
256
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
257
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
258
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
259
+ "model.norm.weight": "model-00002-of-00002.safetensors"
260
+ }
261
+ }
Llama-3.2-3B-GRPO-Indic-v1/checkpoint-100/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23d005aef86d3d2be6c9cb02c545887175d01c19222046b4a6a9e8a7f20bbe3a
3
+ size 12851220766
Llama-3.2-3B-GRPO-Indic-v1/checkpoint-100/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebcd672dc9120ed59604e3c02e6b0ff2683693c075003d93773d14d3cd43a039
3
+ size 14512
Llama-3.2-3B-GRPO-Indic-v1/checkpoint-100/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a7163c9013c6b2ed7e5084a21c517db49d234617bd1526230a694edfcd3c4a3
3
+ size 14512
Llama-3.2-3B-GRPO-Indic-v1/checkpoint-100/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d02012ad52263f70f5b13315011dcba83596bea6efab0a6c49b5380219fc1d8a
3
+ size 1064
Llama-3.2-3B-GRPO-Indic-v1/checkpoint-100/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|eot_id|>"
17
+ }
Llama-3.2-3B-GRPO-Indic-v1/checkpoint-100/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65ff5472d095ccd9332d9e723153d7bc7226cb6be9c1bffda738b5ba2e71bf26
3
+ size 17210084
Llama-3.2-3B-GRPO-Indic-v1/checkpoint-100/tokenizer_config.json ADDED
@@ -0,0 +1,2064 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- if strftime_now is defined %}\n {%- set date_string = strftime_now(\"%d %b %Y\") %}\n {%- else %}\n {%- set date_string = \"26 Jul 2024\" %}\n {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {{- \"<|eot_id|>\" }}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "extra_special_tokens": {},
2057
+ "model_input_names": [
2058
+ "input_ids",
2059
+ "attention_mask"
2060
+ ],
2061
+ "model_max_length": 131072,
2062
+ "pad_token": "<|eot_id|>",
2063
+ "tokenizer_class": "PreTrainedTokenizerFast"
2064
+ }
Llama-3.2-3B-GRPO-Indic-v1/checkpoint-100/trainer_state.json ADDED
@@ -0,0 +1,1733 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.0010375919565871526,
5
+ "eval_steps": 500,
6
+ "global_step": 100,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "completion_length": 333.75,
13
+ "epoch": 1.0375919565871525e-05,
14
+ "grad_norm": 4.6875,
15
+ "kl": 0.0,
16
+ "learning_rate": 1.0375596596804318e-09,
17
+ "loss": -0.0,
18
+ "reward": 2.428252935409546,
19
+ "reward_std": 0.5498241186141968,
20
+ "rewards/combined_metrics_reward": 2.4082529544830322,
21
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
22
+ "rewards/soft_format_reward_func": 0.0,
23
+ "rewards/strict_format_reward_func": 0.0,
24
+ "rewards/xml_structure_reward": 0.0,
25
+ "rewards/xmlcount_reward_func": -0.3799999952316284,
26
+ "step": 1
27
+ },
28
+ {
29
+ "completion_length": 415.125,
30
+ "epoch": 2.075183913174305e-05,
31
+ "grad_norm": 3.625,
32
+ "kl": 0.0,
33
+ "learning_rate": 2.0751193193608636e-09,
34
+ "loss": -0.0,
35
+ "reward": 2.069629669189453,
36
+ "reward_std": 0.5012296438217163,
37
+ "rewards/combined_metrics_reward": 2.278629779815674,
38
+ "rewards/reasoning_quality_reward": 0.3499999940395355,
39
+ "rewards/soft_format_reward_func": 0.0,
40
+ "rewards/strict_format_reward_func": 0.0,
41
+ "rewards/xml_structure_reward": 0.0,
42
+ "rewards/xmlcount_reward_func": -0.5590000152587891,
43
+ "step": 2
44
+ },
45
+ {
46
+ "completion_length": 333.875,
47
+ "epoch": 3.1127758697614576e-05,
48
+ "grad_norm": 4.15625,
49
+ "kl": 0.00031508170650340617,
50
+ "learning_rate": 3.112678979041295e-09,
51
+ "loss": 0.0,
52
+ "reward": 5.483217716217041,
53
+ "reward_std": 0.3646215796470642,
54
+ "rewards/combined_metrics_reward": 5.395092964172363,
55
+ "rewards/reasoning_quality_reward": 0.39800000190734863,
56
+ "rewards/soft_format_reward_func": 0.0,
57
+ "rewards/strict_format_reward_func": 0.0,
58
+ "rewards/xml_structure_reward": 0.0,
59
+ "rewards/xmlcount_reward_func": -0.3098750114440918,
60
+ "step": 3
61
+ },
62
+ {
63
+ "completion_length": 420.375,
64
+ "epoch": 4.15036782634861e-05,
65
+ "grad_norm": 3.859375,
66
+ "kl": 0.00037821970181539655,
67
+ "learning_rate": 4.150238638721727e-09,
68
+ "loss": 0.0,
69
+ "reward": 2.3078813552856445,
70
+ "reward_std": 0.7376255393028259,
71
+ "rewards/combined_metrics_reward": 2.832881450653076,
72
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
73
+ "rewards/soft_format_reward_func": 0.0,
74
+ "rewards/strict_format_reward_func": 0.0,
75
+ "rewards/xml_structure_reward": 0.0,
76
+ "rewards/xmlcount_reward_func": -0.925000011920929,
77
+ "step": 4
78
+ },
79
+ {
80
+ "completion_length": 420.25,
81
+ "epoch": 5.187959782935763e-05,
82
+ "grad_norm": 3.8125,
83
+ "kl": 0.00042366376146674156,
84
+ "learning_rate": 5.1877982984021585e-09,
85
+ "loss": 0.0,
86
+ "reward": 1.3406586647033691,
87
+ "reward_std": 0.670261025428772,
88
+ "rewards/combined_metrics_reward": 1.4642837047576904,
89
+ "rewards/reasoning_quality_reward": 0.3499999940395355,
90
+ "rewards/soft_format_reward_func": 0.0,
91
+ "rewards/strict_format_reward_func": 0.0,
92
+ "rewards/xml_structure_reward": 0.0,
93
+ "rewards/xmlcount_reward_func": -0.4736250042915344,
94
+ "step": 5
95
+ },
96
+ {
97
+ "completion_length": 374.875,
98
+ "epoch": 6.225551739522915e-05,
99
+ "grad_norm": 4.1875,
100
+ "kl": 0.0003987301606684923,
101
+ "learning_rate": 6.22535795808259e-09,
102
+ "loss": 0.0,
103
+ "reward": 2.663606882095337,
104
+ "reward_std": 0.4569581151008606,
105
+ "rewards/combined_metrics_reward": 2.9679818153381348,
106
+ "rewards/reasoning_quality_reward": 0.34700000286102295,
107
+ "rewards/soft_format_reward_func": 0.0,
108
+ "rewards/strict_format_reward_func": 0.0,
109
+ "rewards/xml_structure_reward": 0.0,
110
+ "rewards/xmlcount_reward_func": -0.6513749361038208,
111
+ "step": 6
112
+ },
113
+ {
114
+ "completion_length": 363.125,
115
+ "epoch": 7.263143696110067e-05,
116
+ "grad_norm": 3.640625,
117
+ "kl": 0.0004247631295584142,
118
+ "learning_rate": 7.262917617763022e-09,
119
+ "loss": 0.0,
120
+ "reward": 4.055367946624756,
121
+ "reward_std": 0.6599819660186768,
122
+ "rewards/combined_metrics_reward": 4.261242866516113,
123
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
124
+ "rewards/soft_format_reward_func": 0.0,
125
+ "rewards/strict_format_reward_func": 0.0,
126
+ "rewards/xml_structure_reward": 0.0,
127
+ "rewards/xmlcount_reward_func": -0.6058750152587891,
128
+ "step": 7
129
+ },
130
+ {
131
+ "completion_length": 309.5,
132
+ "epoch": 8.30073565269722e-05,
133
+ "grad_norm": 5.78125,
134
+ "kl": 0.00043861279846169055,
135
+ "learning_rate": 8.300477277443455e-09,
136
+ "loss": 0.0,
137
+ "reward": 2.9705238342285156,
138
+ "reward_std": 0.3289063274860382,
139
+ "rewards/combined_metrics_reward": 2.9382739067077637,
140
+ "rewards/reasoning_quality_reward": 0.34800001978874207,
141
+ "rewards/soft_format_reward_func": 0.0,
142
+ "rewards/strict_format_reward_func": 0.0,
143
+ "rewards/xml_structure_reward": 0.0,
144
+ "rewards/xmlcount_reward_func": -0.31575000286102295,
145
+ "step": 8
146
+ },
147
+ {
148
+ "completion_length": 250.125,
149
+ "epoch": 9.338327609284373e-05,
150
+ "grad_norm": 6.3125,
151
+ "kl": 0.00048099906416609883,
152
+ "learning_rate": 9.338036937123887e-09,
153
+ "loss": -0.0,
154
+ "reward": 6.439043045043945,
155
+ "reward_std": 0.26159030199050903,
156
+ "rewards/combined_metrics_reward": 6.528167724609375,
157
+ "rewards/reasoning_quality_reward": 0.39800000190734863,
158
+ "rewards/soft_format_reward_func": 0.0,
159
+ "rewards/strict_format_reward_func": 0.0,
160
+ "rewards/xml_structure_reward": 0.0,
161
+ "rewards/xmlcount_reward_func": -0.4871250092983246,
162
+ "step": 9
163
+ },
164
+ {
165
+ "completion_length": 217.75,
166
+ "epoch": 0.00010375919565871526,
167
+ "grad_norm": 7.1875,
168
+ "kl": 0.0004605467547662556,
169
+ "learning_rate": 1.0375596596804317e-08,
170
+ "loss": 0.0,
171
+ "reward": 4.732333660125732,
172
+ "reward_std": 0.4634145200252533,
173
+ "rewards/combined_metrics_reward": 4.7409586906433105,
174
+ "rewards/reasoning_quality_reward": 0.3569999933242798,
175
+ "rewards/soft_format_reward_func": 0.0,
176
+ "rewards/strict_format_reward_func": 0.0,
177
+ "rewards/xml_structure_reward": 0.0,
178
+ "rewards/xmlcount_reward_func": -0.3656249940395355,
179
+ "step": 10
180
+ },
181
+ {
182
+ "completion_length": 311.0,
183
+ "epoch": 0.00011413511522458678,
184
+ "grad_norm": 4.84375,
185
+ "kl": 0.0004021780041512102,
186
+ "learning_rate": 1.1413156256484749e-08,
187
+ "loss": 0.0,
188
+ "reward": 4.642187118530273,
189
+ "reward_std": 0.288236528635025,
190
+ "rewards/combined_metrics_reward": 4.849061965942383,
191
+ "rewards/reasoning_quality_reward": 0.3499999940395355,
192
+ "rewards/soft_format_reward_func": 0.0,
193
+ "rewards/strict_format_reward_func": 0.0,
194
+ "rewards/xml_structure_reward": 0.0,
195
+ "rewards/xmlcount_reward_func": -0.5568749904632568,
196
+ "step": 11
197
+ },
198
+ {
199
+ "completion_length": 268.375,
200
+ "epoch": 0.0001245110347904583,
201
+ "grad_norm": 6.1875,
202
+ "kl": 0.00046910648234188557,
203
+ "learning_rate": 1.245071591616518e-08,
204
+ "loss": 0.0,
205
+ "reward": 4.757927894592285,
206
+ "reward_std": 0.5126724243164062,
207
+ "rewards/combined_metrics_reward": 4.876177787780762,
208
+ "rewards/reasoning_quality_reward": 0.3850000202655792,
209
+ "rewards/soft_format_reward_func": 0.0,
210
+ "rewards/strict_format_reward_func": 0.0,
211
+ "rewards/xml_structure_reward": 0.0,
212
+ "rewards/xmlcount_reward_func": -0.503250002861023,
213
+ "step": 12
214
+ },
215
+ {
216
+ "completion_length": 250.875,
217
+ "epoch": 0.00013488695435632983,
218
+ "grad_norm": 5.46875,
219
+ "kl": 0.00044920743675902486,
220
+ "learning_rate": 1.3488275575845613e-08,
221
+ "loss": 0.0,
222
+ "reward": 6.194243907928467,
223
+ "reward_std": 0.13808226585388184,
224
+ "rewards/combined_metrics_reward": 6.306493759155273,
225
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
226
+ "rewards/soft_format_reward_func": 0.0,
227
+ "rewards/strict_format_reward_func": 0.0,
228
+ "rewards/xml_structure_reward": 0.0,
229
+ "rewards/xmlcount_reward_func": -0.5122500061988831,
230
+ "step": 13
231
+ },
232
+ {
233
+ "completion_length": 301.375,
234
+ "epoch": 0.00014526287392220135,
235
+ "grad_norm": 3.515625,
236
+ "kl": 0.00032219121931120753,
237
+ "learning_rate": 1.4525835235526043e-08,
238
+ "loss": 0.0,
239
+ "reward": 5.817522048950195,
240
+ "reward_std": 0.36358317732810974,
241
+ "rewards/combined_metrics_reward": 5.911397457122803,
242
+ "rewards/reasoning_quality_reward": 0.3499999940395355,
243
+ "rewards/soft_format_reward_func": 0.0,
244
+ "rewards/strict_format_reward_func": 0.0,
245
+ "rewards/xml_structure_reward": 0.0,
246
+ "rewards/xmlcount_reward_func": -0.4438749849796295,
247
+ "step": 14
248
+ },
249
+ {
250
+ "completion_length": 236.75,
251
+ "epoch": 0.00015563879348807287,
252
+ "grad_norm": 4.28125,
253
+ "kl": 0.00034530123230069876,
254
+ "learning_rate": 1.5563394895206475e-08,
255
+ "loss": 0.0,
256
+ "reward": 6.109199523925781,
257
+ "reward_std": 0.38126617670059204,
258
+ "rewards/combined_metrics_reward": 5.87032413482666,
259
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
260
+ "rewards/soft_format_reward_func": 0.0,
261
+ "rewards/strict_format_reward_func": 0.0,
262
+ "rewards/xml_structure_reward": 0.0,
263
+ "rewards/xmlcount_reward_func": -0.16112500429153442,
264
+ "step": 15
265
+ },
266
+ {
267
+ "completion_length": 300.75,
268
+ "epoch": 0.0001660147130539444,
269
+ "grad_norm": 4.15625,
270
+ "kl": 0.00042490597115829587,
271
+ "learning_rate": 1.660095455488691e-08,
272
+ "loss": 0.0,
273
+ "reward": 3.778770685195923,
274
+ "reward_std": 0.3859076201915741,
275
+ "rewards/combined_metrics_reward": 3.4963955879211426,
276
+ "rewards/reasoning_quality_reward": 0.2840000092983246,
277
+ "rewards/soft_format_reward_func": 0.0,
278
+ "rewards/strict_format_reward_func": 0.0,
279
+ "rewards/xml_structure_reward": 0.0,
280
+ "rewards/xmlcount_reward_func": -0.0016249967738986015,
281
+ "step": 16
282
+ },
283
+ {
284
+ "completion_length": 273.125,
285
+ "epoch": 0.00017639063261981592,
286
+ "grad_norm": 6.0,
287
+ "kl": 0.0005725660594180226,
288
+ "learning_rate": 1.763851421456734e-08,
289
+ "loss": 0.0,
290
+ "reward": 3.188627004623413,
291
+ "reward_std": 0.4401717483997345,
292
+ "rewards/combined_metrics_reward": 3.121127128601074,
293
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
294
+ "rewards/soft_format_reward_func": 0.0,
295
+ "rewards/strict_format_reward_func": 0.0,
296
+ "rewards/xml_structure_reward": 0.0,
297
+ "rewards/xmlcount_reward_func": -0.33249998092651367,
298
+ "step": 17
299
+ },
300
+ {
301
+ "completion_length": 338.25,
302
+ "epoch": 0.00018676655218568747,
303
+ "grad_norm": 4.28125,
304
+ "kl": 0.0005062771961092949,
305
+ "learning_rate": 1.8676073874247773e-08,
306
+ "loss": 0.0,
307
+ "reward": 3.8921751976013184,
308
+ "reward_std": 0.49976158142089844,
309
+ "rewards/combined_metrics_reward": 4.043675422668457,
310
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
311
+ "rewards/soft_format_reward_func": 0.0,
312
+ "rewards/strict_format_reward_func": 0.0,
313
+ "rewards/xml_structure_reward": 0.0,
314
+ "rewards/xmlcount_reward_func": -0.5514999628067017,
315
+ "step": 18
316
+ },
317
+ {
318
+ "completion_length": 257.125,
319
+ "epoch": 0.000197142471751559,
320
+ "grad_norm": 4.03125,
321
+ "kl": 0.0003546299412846565,
322
+ "learning_rate": 1.9713633533928203e-08,
323
+ "loss": -0.0,
324
+ "reward": 6.701379776000977,
325
+ "reward_std": 0.32936251163482666,
326
+ "rewards/combined_metrics_reward": 6.6538801193237305,
327
+ "rewards/reasoning_quality_reward": 0.3499999940395355,
328
+ "rewards/soft_format_reward_func": 0.0,
329
+ "rewards/strict_format_reward_func": 0.0,
330
+ "rewards/xml_structure_reward": 0.0,
331
+ "rewards/xmlcount_reward_func": -0.30250000953674316,
332
+ "step": 19
333
+ },
334
+ {
335
+ "completion_length": 379.125,
336
+ "epoch": 0.00020751839131743051,
337
+ "grad_norm": 3.109375,
338
+ "kl": 0.0003599152551032603,
339
+ "learning_rate": 2.0751193193608634e-08,
340
+ "loss": 0.0,
341
+ "reward": 2.5460047721862793,
342
+ "reward_std": 0.4278355836868286,
343
+ "rewards/combined_metrics_reward": 2.629004716873169,
344
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
345
+ "rewards/soft_format_reward_func": 0.0,
346
+ "rewards/strict_format_reward_func": 0.0,
347
+ "rewards/xml_structure_reward": 0.0,
348
+ "rewards/xmlcount_reward_func": -0.4830000102519989,
349
+ "step": 20
350
+ },
351
+ {
352
+ "completion_length": 367.875,
353
+ "epoch": 0.00021789431088330204,
354
+ "grad_norm": 4.0625,
355
+ "kl": 0.000419655378209427,
356
+ "learning_rate": 2.1788752853289068e-08,
357
+ "loss": 0.0,
358
+ "reward": 4.129725456237793,
359
+ "reward_std": 0.5266568064689636,
360
+ "rewards/combined_metrics_reward": 4.187850475311279,
361
+ "rewards/reasoning_quality_reward": 0.3499999940395355,
362
+ "rewards/soft_format_reward_func": 0.0,
363
+ "rewards/strict_format_reward_func": 0.0,
364
+ "rewards/xml_structure_reward": 0.0,
365
+ "rewards/xmlcount_reward_func": -0.40812501311302185,
366
+ "step": 21
367
+ },
368
+ {
369
+ "completion_length": 256.25,
370
+ "epoch": 0.00022827023044917356,
371
+ "grad_norm": 4.15625,
372
+ "kl": 0.00039975615800358355,
373
+ "learning_rate": 2.2826312512969498e-08,
374
+ "loss": 0.0,
375
+ "reward": 4.17482328414917,
376
+ "reward_std": 0.31743156909942627,
377
+ "rewards/combined_metrics_reward": 4.0281982421875,
378
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
379
+ "rewards/soft_format_reward_func": 0.0,
380
+ "rewards/strict_format_reward_func": 0.0,
381
+ "rewards/xml_structure_reward": 0.0,
382
+ "rewards/xmlcount_reward_func": -0.25337502360343933,
383
+ "step": 22
384
+ },
385
+ {
386
+ "completion_length": 323.25,
387
+ "epoch": 0.00023864615001504508,
388
+ "grad_norm": 3.5,
389
+ "kl": 0.00040266913129016757,
390
+ "learning_rate": 2.3863872172649928e-08,
391
+ "loss": 0.0,
392
+ "reward": 4.960608959197998,
393
+ "reward_std": 0.3813040256500244,
394
+ "rewards/combined_metrics_reward": 5.068108558654785,
395
+ "rewards/reasoning_quality_reward": 0.37599998712539673,
396
+ "rewards/soft_format_reward_func": 0.0,
397
+ "rewards/strict_format_reward_func": 0.0,
398
+ "rewards/xml_structure_reward": 0.0,
399
+ "rewards/xmlcount_reward_func": -0.48350000381469727,
400
+ "step": 23
401
+ },
402
+ {
403
+ "completion_length": 230.625,
404
+ "epoch": 0.0002490220695809166,
405
+ "grad_norm": 5.0,
406
+ "kl": 0.0005796175682917237,
407
+ "learning_rate": 2.490143183233036e-08,
408
+ "loss": 0.0,
409
+ "reward": 5.720316410064697,
410
+ "reward_std": 0.2986779808998108,
411
+ "rewards/combined_metrics_reward": 5.365566253662109,
412
+ "rewards/reasoning_quality_reward": 0.3889999985694885,
413
+ "rewards/soft_format_reward_func": 0.0,
414
+ "rewards/strict_format_reward_func": 0.0,
415
+ "rewards/xml_structure_reward": 0.0,
416
+ "rewards/xmlcount_reward_func": -0.03425000235438347,
417
+ "step": 24
418
+ },
419
+ {
420
+ "completion_length": 280.75,
421
+ "epoch": 0.00025939798914678816,
422
+ "grad_norm": 5.28125,
423
+ "kl": 0.0005220682942308486,
424
+ "learning_rate": 2.5938991492010796e-08,
425
+ "loss": 0.0,
426
+ "reward": 3.323814868927002,
427
+ "reward_std": 0.43842071294784546,
428
+ "rewards/combined_metrics_reward": 3.1951897144317627,
429
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
430
+ "rewards/soft_format_reward_func": 0.0,
431
+ "rewards/strict_format_reward_func": 0.0,
432
+ "rewards/xml_structure_reward": 0.0,
433
+ "rewards/xmlcount_reward_func": -0.27137500047683716,
434
+ "step": 25
435
+ },
436
+ {
437
+ "completion_length": 350.75,
438
+ "epoch": 0.00026977390871265965,
439
+ "grad_norm": 3.96875,
440
+ "kl": 0.0004046727844979614,
441
+ "learning_rate": 2.6976551151691226e-08,
442
+ "loss": 0.0,
443
+ "reward": 2.652538776397705,
444
+ "reward_std": 0.4477674067020416,
445
+ "rewards/combined_metrics_reward": 2.6144137382507324,
446
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
447
+ "rewards/soft_format_reward_func": 0.0,
448
+ "rewards/strict_format_reward_func": 0.0,
449
+ "rewards/xml_structure_reward": 0.0,
450
+ "rewards/xmlcount_reward_func": -0.3618749976158142,
451
+ "step": 26
452
+ },
453
+ {
454
+ "completion_length": 376.125,
455
+ "epoch": 0.0002801498282785312,
456
+ "grad_norm": 4.09375,
457
+ "kl": 0.0004263470182195306,
458
+ "learning_rate": 2.8014110811371656e-08,
459
+ "loss": 0.0,
460
+ "reward": 3.5168190002441406,
461
+ "reward_std": 0.4238409399986267,
462
+ "rewards/combined_metrics_reward": 3.790194034576416,
463
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
464
+ "rewards/soft_format_reward_func": 0.0,
465
+ "rewards/strict_format_reward_func": 0.0,
466
+ "rewards/xml_structure_reward": 0.0,
467
+ "rewards/xmlcount_reward_func": -0.6733750104904175,
468
+ "step": 27
469
+ },
470
+ {
471
+ "completion_length": 359.375,
472
+ "epoch": 0.0002905257478444027,
473
+ "grad_norm": 4.78125,
474
+ "kl": 0.0005214965203776956,
475
+ "learning_rate": 2.9051670471052087e-08,
476
+ "loss": 0.0,
477
+ "reward": 2.9417853355407715,
478
+ "reward_std": 0.638547420501709,
479
+ "rewards/combined_metrics_reward": 3.055910587310791,
480
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
481
+ "rewards/soft_format_reward_func": 0.0,
482
+ "rewards/strict_format_reward_func": 0.0,
483
+ "rewards/xml_structure_reward": 0.0,
484
+ "rewards/xmlcount_reward_func": -0.5141249895095825,
485
+ "step": 28
486
+ },
487
+ {
488
+ "completion_length": 364.375,
489
+ "epoch": 0.00030090166741027425,
490
+ "grad_norm": 4.0,
491
+ "kl": 0.00038014992605894804,
492
+ "learning_rate": 3.008923013073252e-08,
493
+ "loss": -0.0,
494
+ "reward": 3.8992490768432617,
495
+ "reward_std": 0.6337953209877014,
496
+ "rewards/combined_metrics_reward": 4.057999134063721,
497
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
498
+ "rewards/soft_format_reward_func": 0.0,
499
+ "rewards/strict_format_reward_func": 0.0,
500
+ "rewards/xml_structure_reward": 0.0,
501
+ "rewards/xmlcount_reward_func": -0.5587500333786011,
502
+ "step": 29
503
+ },
504
+ {
505
+ "completion_length": 261.625,
506
+ "epoch": 0.00031127758697614574,
507
+ "grad_norm": 4.3125,
508
+ "kl": 0.00045962046715430915,
509
+ "learning_rate": 3.112678979041295e-08,
510
+ "loss": 0.0,
511
+ "reward": 2.532193422317505,
512
+ "reward_std": 0.35507291555404663,
513
+ "rewards/combined_metrics_reward": 2.3344433307647705,
514
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
515
+ "rewards/soft_format_reward_func": 0.0,
516
+ "rewards/strict_format_reward_func": 0.0,
517
+ "rewards/xml_structure_reward": 0.0,
518
+ "rewards/xmlcount_reward_func": -0.20224997401237488,
519
+ "step": 30
520
+ },
521
+ {
522
+ "completion_length": 335.25,
523
+ "epoch": 0.0003216535065420173,
524
+ "grad_norm": 4.09375,
525
+ "kl": 0.00046017125714570284,
526
+ "learning_rate": 3.216434945009338e-08,
527
+ "loss": 0.0,
528
+ "reward": 4.070613384246826,
529
+ "reward_std": 0.32982319593429565,
530
+ "rewards/combined_metrics_reward": 3.9483633041381836,
531
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
532
+ "rewards/soft_format_reward_func": 0.0,
533
+ "rewards/strict_format_reward_func": 0.0,
534
+ "rewards/xml_structure_reward": 0.0,
535
+ "rewards/xmlcount_reward_func": -0.2777499854564667,
536
+ "step": 31
537
+ },
538
+ {
539
+ "completion_length": 326.5,
540
+ "epoch": 0.0003320294261078888,
541
+ "grad_norm": 4.0,
542
+ "kl": 0.0004428713000379503,
543
+ "learning_rate": 3.320190910977382e-08,
544
+ "loss": 0.0,
545
+ "reward": 3.0092625617980957,
546
+ "reward_std": 0.31660038232803345,
547
+ "rewards/combined_metrics_reward": 3.1851377487182617,
548
+ "rewards/reasoning_quality_reward": 0.3499999940395355,
549
+ "rewards/soft_format_reward_func": 0.0,
550
+ "rewards/strict_format_reward_func": 0.0,
551
+ "rewards/xml_structure_reward": 0.0,
552
+ "rewards/xmlcount_reward_func": -0.5258749723434448,
553
+ "step": 32
554
+ },
555
+ {
556
+ "completion_length": 284.75,
557
+ "epoch": 0.00034240534567376034,
558
+ "grad_norm": 4.65625,
559
+ "kl": 0.0003916996356565505,
560
+ "learning_rate": 3.423946876945425e-08,
561
+ "loss": -0.0,
562
+ "reward": 3.173705577850342,
563
+ "reward_std": 0.13702140748500824,
564
+ "rewards/combined_metrics_reward": 3.0269558429718018,
565
+ "rewards/reasoning_quality_reward": 0.3789999783039093,
566
+ "rewards/soft_format_reward_func": 0.0,
567
+ "rewards/strict_format_reward_func": 0.0,
568
+ "rewards/xml_structure_reward": 0.0,
569
+ "rewards/xmlcount_reward_func": -0.23225000500679016,
570
+ "step": 33
571
+ },
572
+ {
573
+ "completion_length": 278.125,
574
+ "epoch": 0.00035278126523963184,
575
+ "grad_norm": 4.09375,
576
+ "kl": 0.00037749818875454366,
577
+ "learning_rate": 3.527702842913468e-08,
578
+ "loss": 0.0,
579
+ "reward": 5.403405666351318,
580
+ "reward_std": 0.41309595108032227,
581
+ "rewards/combined_metrics_reward": 5.1726555824279785,
582
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
583
+ "rewards/soft_format_reward_func": 0.0,
584
+ "rewards/strict_format_reward_func": 0.0,
585
+ "rewards/xml_structure_reward": 0.0,
586
+ "rewards/xmlcount_reward_func": -0.1692499965429306,
587
+ "step": 34
588
+ },
589
+ {
590
+ "completion_length": 237.875,
591
+ "epoch": 0.0003631571848055034,
592
+ "grad_norm": 6.65625,
593
+ "kl": 0.00043712399201467633,
594
+ "learning_rate": 3.631458808881511e-08,
595
+ "loss": -0.0,
596
+ "reward": 6.74604606628418,
597
+ "reward_std": 0.21016466617584229,
598
+ "rewards/combined_metrics_reward": 6.769796371459961,
599
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
600
+ "rewards/soft_format_reward_func": 0.0,
601
+ "rewards/strict_format_reward_func": 0.0,
602
+ "rewards/xml_structure_reward": 0.0,
603
+ "rewards/xmlcount_reward_func": -0.42375001311302185,
604
+ "step": 35
605
+ },
606
+ {
607
+ "completion_length": 269.125,
608
+ "epoch": 0.00037353310437137494,
609
+ "grad_norm": 3.796875,
610
+ "kl": 0.00025458994787186384,
611
+ "learning_rate": 3.7352147748495546e-08,
612
+ "loss": 0.0,
613
+ "reward": 6.012961387634277,
614
+ "reward_std": 0.3911527693271637,
615
+ "rewards/combined_metrics_reward": 5.944836139678955,
616
+ "rewards/reasoning_quality_reward": 0.39800000190734863,
617
+ "rewards/soft_format_reward_func": 0.0,
618
+ "rewards/strict_format_reward_func": 0.0,
619
+ "rewards/xml_structure_reward": 0.0,
620
+ "rewards/xmlcount_reward_func": -0.32987499237060547,
621
+ "step": 36
622
+ },
623
+ {
624
+ "completion_length": 400.125,
625
+ "epoch": 0.00038390902393724643,
626
+ "grad_norm": 3.90625,
627
+ "kl": 0.0004260237328708172,
628
+ "learning_rate": 3.8389707408175977e-08,
629
+ "loss": 0.0,
630
+ "reward": 2.2903735637664795,
631
+ "reward_std": 0.5587140917778015,
632
+ "rewards/combined_metrics_reward": 2.426248550415039,
633
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
634
+ "rewards/soft_format_reward_func": 0.0,
635
+ "rewards/strict_format_reward_func": 0.0,
636
+ "rewards/xml_structure_reward": 0.0,
637
+ "rewards/xmlcount_reward_func": -0.5358749628067017,
638
+ "step": 37
639
+ },
640
+ {
641
+ "completion_length": 370.75,
642
+ "epoch": 0.000394284943503118,
643
+ "grad_norm": 3.53125,
644
+ "kl": 0.00045743334339931607,
645
+ "learning_rate": 3.942726706785641e-08,
646
+ "loss": 0.0,
647
+ "reward": 3.3162245750427246,
648
+ "reward_std": 0.39514103531837463,
649
+ "rewards/combined_metrics_reward": 3.5430994033813477,
650
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
651
+ "rewards/soft_format_reward_func": 0.0,
652
+ "rewards/strict_format_reward_func": 0.0,
653
+ "rewards/xml_structure_reward": 0.0,
654
+ "rewards/xmlcount_reward_func": -0.6268749833106995,
655
+ "step": 38
656
+ },
657
+ {
658
+ "completion_length": 257.75,
659
+ "epoch": 0.0004046608630689895,
660
+ "grad_norm": 4.8125,
661
+ "kl": 0.00036271530552767217,
662
+ "learning_rate": 4.046482672753684e-08,
663
+ "loss": 0.0,
664
+ "reward": 4.9680376052856445,
665
+ "reward_std": 0.2537137269973755,
666
+ "rewards/combined_metrics_reward": 4.803162574768066,
667
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
668
+ "rewards/soft_format_reward_func": 0.0,
669
+ "rewards/strict_format_reward_func": 0.0,
670
+ "rewards/xml_structure_reward": 0.0,
671
+ "rewards/xmlcount_reward_func": -0.23512500524520874,
672
+ "step": 39
673
+ },
674
+ {
675
+ "completion_length": 346.625,
676
+ "epoch": 0.00041503678263486103,
677
+ "grad_norm": 3.734375,
678
+ "kl": 0.000414666545111686,
679
+ "learning_rate": 4.150238638721727e-08,
680
+ "loss": 0.0,
681
+ "reward": 2.7971127033233643,
682
+ "reward_std": 0.5673857927322388,
683
+ "rewards/combined_metrics_reward": 2.839237689971924,
684
+ "rewards/reasoning_quality_reward": 0.3499999940395355,
685
+ "rewards/soft_format_reward_func": 0.0,
686
+ "rewards/strict_format_reward_func": 0.0,
687
+ "rewards/xml_structure_reward": 0.0,
688
+ "rewards/xmlcount_reward_func": -0.3921250104904175,
689
+ "step": 40
690
+ },
691
+ {
692
+ "completion_length": 265.0,
693
+ "epoch": 0.0004254127022007325,
694
+ "grad_norm": 3.8125,
695
+ "kl": 0.00040037892176769674,
696
+ "learning_rate": 4.25399460468977e-08,
697
+ "loss": 0.0,
698
+ "reward": 6.041917324066162,
699
+ "reward_std": 0.6179963946342468,
700
+ "rewards/combined_metrics_reward": 6.086292266845703,
701
+ "rewards/reasoning_quality_reward": 0.38099998235702515,
702
+ "rewards/soft_format_reward_func": 0.0,
703
+ "rewards/strict_format_reward_func": 0.0,
704
+ "rewards/xml_structure_reward": 0.0,
705
+ "rewards/xmlcount_reward_func": -0.42537498474121094,
706
+ "step": 41
707
+ },
708
+ {
709
+ "completion_length": 281.25,
710
+ "epoch": 0.0004357886217666041,
711
+ "grad_norm": 4.6875,
712
+ "kl": 0.00042478268733248115,
713
+ "learning_rate": 4.3577505706578135e-08,
714
+ "loss": 0.0,
715
+ "reward": 3.5850915908813477,
716
+ "reward_std": 0.3067721426486969,
717
+ "rewards/combined_metrics_reward": 3.4888415336608887,
718
+ "rewards/reasoning_quality_reward": 0.3789999783039093,
719
+ "rewards/soft_format_reward_func": 0.0,
720
+ "rewards/strict_format_reward_func": 0.0,
721
+ "rewards/xml_structure_reward": 0.0,
722
+ "rewards/xmlcount_reward_func": -0.2827500104904175,
723
+ "step": 42
724
+ },
725
+ {
726
+ "completion_length": 299.25,
727
+ "epoch": 0.00044616454133247557,
728
+ "grad_norm": 4.0,
729
+ "kl": 0.0003129114047624171,
730
+ "learning_rate": 4.4615065366258565e-08,
731
+ "loss": -0.0,
732
+ "reward": 4.075703144073486,
733
+ "reward_std": 0.13395221531391144,
734
+ "rewards/combined_metrics_reward": 3.734328269958496,
735
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
736
+ "rewards/soft_format_reward_func": 0.0,
737
+ "rewards/strict_format_reward_func": 0.0,
738
+ "rewards/xml_structure_reward": 0.0,
739
+ "rewards/xmlcount_reward_func": -0.058625005185604095,
740
+ "step": 43
741
+ },
742
+ {
743
+ "completion_length": 329.75,
744
+ "epoch": 0.0004565404608983471,
745
+ "grad_norm": 4.78125,
746
+ "kl": 0.00039643797208555043,
747
+ "learning_rate": 4.5652625025938996e-08,
748
+ "loss": 0.0,
749
+ "reward": 5.387487411499023,
750
+ "reward_std": 0.29496538639068604,
751
+ "rewards/combined_metrics_reward": 5.274112224578857,
752
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
753
+ "rewards/soft_format_reward_func": 0.0,
754
+ "rewards/strict_format_reward_func": 0.0,
755
+ "rewards/xml_structure_reward": 0.0,
756
+ "rewards/xmlcount_reward_func": -0.2866249978542328,
757
+ "step": 44
758
+ },
759
+ {
760
+ "completion_length": 260.5,
761
+ "epoch": 0.0004669163804642186,
762
+ "grad_norm": 4.84375,
763
+ "kl": 0.0003711177268996835,
764
+ "learning_rate": 4.6690184685619426e-08,
765
+ "loss": 0.0,
766
+ "reward": 3.599208354949951,
767
+ "reward_std": 0.2509615421295166,
768
+ "rewards/combined_metrics_reward": 3.5150833129882812,
769
+ "rewards/reasoning_quality_reward": 0.34700000286102295,
770
+ "rewards/soft_format_reward_func": 0.0,
771
+ "rewards/strict_format_reward_func": 0.0,
772
+ "rewards/xml_structure_reward": 0.0,
773
+ "rewards/xmlcount_reward_func": -0.2628749907016754,
774
+ "step": 45
775
+ },
776
+ {
777
+ "completion_length": 245.25,
778
+ "epoch": 0.00047729230003009017,
779
+ "grad_norm": 4.9375,
780
+ "kl": 0.0003939840826205909,
781
+ "learning_rate": 4.7727744345299857e-08,
782
+ "loss": 0.0,
783
+ "reward": 5.209469795227051,
784
+ "reward_std": 0.47956180572509766,
785
+ "rewards/combined_metrics_reward": 5.167594909667969,
786
+ "rewards/reasoning_quality_reward": 0.3499999940395355,
787
+ "rewards/soft_format_reward_func": 0.0,
788
+ "rewards/strict_format_reward_func": 0.0,
789
+ "rewards/xml_structure_reward": 0.0,
790
+ "rewards/xmlcount_reward_func": -0.30812498927116394,
791
+ "step": 46
792
+ },
793
+ {
794
+ "completion_length": 267.875,
795
+ "epoch": 0.0004876682195959617,
796
+ "grad_norm": 4.40625,
797
+ "kl": 0.00034818187123164535,
798
+ "learning_rate": 4.876530400498029e-08,
799
+ "loss": 0.0,
800
+ "reward": 6.008094310760498,
801
+ "reward_std": 0.31677666306495667,
802
+ "rewards/combined_metrics_reward": 5.824219703674316,
803
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
804
+ "rewards/soft_format_reward_func": 0.0,
805
+ "rewards/strict_format_reward_func": 0.0,
806
+ "rewards/xml_structure_reward": 0.0,
807
+ "rewards/xmlcount_reward_func": -0.2161250114440918,
808
+ "step": 47
809
+ },
810
+ {
811
+ "completion_length": 273.25,
812
+ "epoch": 0.0004980441391618332,
813
+ "grad_norm": 4.4375,
814
+ "kl": 0.0003960896283388138,
815
+ "learning_rate": 4.980286366466072e-08,
816
+ "loss": 0.0,
817
+ "reward": 3.8868627548217773,
818
+ "reward_std": 0.4210134744644165,
819
+ "rewards/combined_metrics_reward": 3.9131126403808594,
820
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
821
+ "rewards/soft_format_reward_func": 0.0,
822
+ "rewards/strict_format_reward_func": 0.0,
823
+ "rewards/xml_structure_reward": 0.0,
824
+ "rewards/xmlcount_reward_func": -0.42624998092651367,
825
+ "step": 48
826
+ },
827
+ {
828
+ "completion_length": 326.625,
829
+ "epoch": 0.0005084200587277048,
830
+ "grad_norm": 4.53125,
831
+ "kl": 0.0002970965579152107,
832
+ "learning_rate": 5.084042332434116e-08,
833
+ "loss": -0.0,
834
+ "reward": 7.0499773025512695,
835
+ "reward_std": 0.43009862303733826,
836
+ "rewards/combined_metrics_reward": 7.161852836608887,
837
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
838
+ "rewards/soft_format_reward_func": 0.0,
839
+ "rewards/strict_format_reward_func": 0.0,
840
+ "rewards/xml_structure_reward": 0.0,
841
+ "rewards/xmlcount_reward_func": -0.5118750333786011,
842
+ "step": 49
843
+ },
844
+ {
845
+ "completion_length": 236.5,
846
+ "epoch": 0.0005187959782935763,
847
+ "grad_norm": 5.53125,
848
+ "kl": 0.00041614353540353477,
849
+ "learning_rate": 5.187798298402159e-08,
850
+ "loss": 0.0,
851
+ "reward": 5.3163604736328125,
852
+ "reward_std": 0.2907780408859253,
853
+ "rewards/combined_metrics_reward": 5.211610317230225,
854
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
855
+ "rewards/soft_format_reward_func": 0.0,
856
+ "rewards/strict_format_reward_func": 0.0,
857
+ "rewards/xml_structure_reward": 0.0,
858
+ "rewards/xmlcount_reward_func": -0.2952499985694885,
859
+ "step": 50
860
+ },
861
+ {
862
+ "completion_length": 297.25,
863
+ "epoch": 0.0005291718978594478,
864
+ "grad_norm": 5.875,
865
+ "kl": 0.0005030147731304169,
866
+ "learning_rate": 5.291554264370202e-08,
867
+ "loss": 0.0,
868
+ "reward": 3.280449628829956,
869
+ "reward_std": 0.4011386036872864,
870
+ "rewards/combined_metrics_reward": 3.4379496574401855,
871
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
872
+ "rewards/soft_format_reward_func": 0.0,
873
+ "rewards/strict_format_reward_func": 0.0,
874
+ "rewards/xml_structure_reward": 0.0,
875
+ "rewards/xmlcount_reward_func": -0.5575000047683716,
876
+ "step": 51
877
+ },
878
+ {
879
+ "completion_length": 386.875,
880
+ "epoch": 0.0005395478174253193,
881
+ "grad_norm": 4.96875,
882
+ "kl": 0.0003959759487770498,
883
+ "learning_rate": 5.395310230338245e-08,
884
+ "loss": 0.0,
885
+ "reward": 3.6646573543548584,
886
+ "reward_std": 0.5163489580154419,
887
+ "rewards/combined_metrics_reward": 3.823282241821289,
888
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
889
+ "rewards/soft_format_reward_func": 0.0,
890
+ "rewards/strict_format_reward_func": 0.0,
891
+ "rewards/xml_structure_reward": 0.0,
892
+ "rewards/xmlcount_reward_func": -0.5586249828338623,
893
+ "step": 52
894
+ },
895
+ {
896
+ "completion_length": 263.75,
897
+ "epoch": 0.0005499237369911909,
898
+ "grad_norm": 4.21875,
899
+ "kl": 0.0003840731515083462,
900
+ "learning_rate": 5.499066196306288e-08,
901
+ "loss": 0.0,
902
+ "reward": 5.555856704711914,
903
+ "reward_std": 0.44427379965782166,
904
+ "rewards/combined_metrics_reward": 5.382356643676758,
905
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
906
+ "rewards/soft_format_reward_func": 0.0,
907
+ "rewards/strict_format_reward_func": 0.0,
908
+ "rewards/xml_structure_reward": 0.0,
909
+ "rewards/xmlcount_reward_func": -0.226500004529953,
910
+ "step": 53
911
+ },
912
+ {
913
+ "completion_length": 254.5,
914
+ "epoch": 0.0005602996565570624,
915
+ "grad_norm": 4.78125,
916
+ "kl": 0.00039330628351308405,
917
+ "learning_rate": 5.602822162274331e-08,
918
+ "loss": -0.0,
919
+ "reward": 7.4290008544921875,
920
+ "reward_std": 0.08576694130897522,
921
+ "rewards/combined_metrics_reward": 7.625250816345215,
922
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
923
+ "rewards/soft_format_reward_func": 0.0,
924
+ "rewards/strict_format_reward_func": 0.0,
925
+ "rewards/xml_structure_reward": 0.0,
926
+ "rewards/xmlcount_reward_func": -0.5962499976158142,
927
+ "step": 54
928
+ },
929
+ {
930
+ "completion_length": 219.875,
931
+ "epoch": 0.0005706755761229338,
932
+ "grad_norm": 4.53125,
933
+ "kl": 0.00039344612741842866,
934
+ "learning_rate": 5.706578128242374e-08,
935
+ "loss": -0.0,
936
+ "reward": 6.296121597290039,
937
+ "reward_std": 0.2410733997821808,
938
+ "rewards/combined_metrics_reward": 6.115996837615967,
939
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
940
+ "rewards/soft_format_reward_func": 0.0,
941
+ "rewards/strict_format_reward_func": 0.0,
942
+ "rewards/xml_structure_reward": 0.0,
943
+ "rewards/xmlcount_reward_func": -0.2198750078678131,
944
+ "step": 55
945
+ },
946
+ {
947
+ "completion_length": 268.25,
948
+ "epoch": 0.0005810514956888054,
949
+ "grad_norm": 4.59375,
950
+ "kl": 0.00035610812483355403,
951
+ "learning_rate": 5.8103340942104173e-08,
952
+ "loss": -0.0,
953
+ "reward": 6.83819580078125,
954
+ "reward_std": 0.2518574893474579,
955
+ "rewards/combined_metrics_reward": 6.931446075439453,
956
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
957
+ "rewards/soft_format_reward_func": 0.0,
958
+ "rewards/strict_format_reward_func": 0.0,
959
+ "rewards/xml_structure_reward": 0.0,
960
+ "rewards/xmlcount_reward_func": -0.4932500123977661,
961
+ "step": 56
962
+ },
963
+ {
964
+ "completion_length": 304.125,
965
+ "epoch": 0.0005914274152546769,
966
+ "grad_norm": 4.40625,
967
+ "kl": 0.0003948260855395347,
968
+ "learning_rate": 5.914090060178461e-08,
969
+ "loss": -0.0,
970
+ "reward": 4.632381439208984,
971
+ "reward_std": 0.21780481934547424,
972
+ "rewards/combined_metrics_reward": 4.602256774902344,
973
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
974
+ "rewards/soft_format_reward_func": 0.0,
975
+ "rewards/strict_format_reward_func": 0.0,
976
+ "rewards/xml_structure_reward": 0.0,
977
+ "rewards/xmlcount_reward_func": -0.3698750138282776,
978
+ "step": 57
979
+ },
980
+ {
981
+ "completion_length": 313.75,
982
+ "epoch": 0.0006018033348205485,
983
+ "grad_norm": 4.875,
984
+ "kl": 0.00047028501285240054,
985
+ "learning_rate": 6.017846026146504e-08,
986
+ "loss": 0.0,
987
+ "reward": 3.2705395221710205,
988
+ "reward_std": 0.32830536365509033,
989
+ "rewards/combined_metrics_reward": 3.2600395679473877,
990
+ "rewards/reasoning_quality_reward": 0.3790000081062317,
991
+ "rewards/soft_format_reward_func": 0.0,
992
+ "rewards/strict_format_reward_func": 0.0,
993
+ "rewards/xml_structure_reward": 0.0,
994
+ "rewards/xmlcount_reward_func": -0.3684999942779541,
995
+ "step": 58
996
+ },
997
+ {
998
+ "completion_length": 529.625,
999
+ "epoch": 0.00061217925438642,
1000
+ "grad_norm": 5.21875,
1001
+ "kl": 0.0004046802641823888,
1002
+ "learning_rate": 6.121601992114547e-08,
1003
+ "loss": 0.0,
1004
+ "reward": 1.5312831401824951,
1005
+ "reward_std": 0.5027981400489807,
1006
+ "rewards/combined_metrics_reward": 2.0016582012176514,
1007
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
1008
+ "rewards/soft_format_reward_func": 0.0,
1009
+ "rewards/strict_format_reward_func": 0.0,
1010
+ "rewards/xml_structure_reward": 0.0,
1011
+ "rewards/xmlcount_reward_func": -0.8703750371932983,
1012
+ "step": 59
1013
+ },
1014
+ {
1015
+ "completion_length": 304.625,
1016
+ "epoch": 0.0006225551739522915,
1017
+ "grad_norm": 4.21875,
1018
+ "kl": 0.00040757792885415256,
1019
+ "learning_rate": 6.22535795808259e-08,
1020
+ "loss": 0.0,
1021
+ "reward": 3.95377516746521,
1022
+ "reward_std": 0.37445712089538574,
1023
+ "rewards/combined_metrics_reward": 3.8430252075195312,
1024
+ "rewards/reasoning_quality_reward": 0.3959999978542328,
1025
+ "rewards/soft_format_reward_func": 0.0,
1026
+ "rewards/strict_format_reward_func": 0.0,
1027
+ "rewards/xml_structure_reward": 0.0,
1028
+ "rewards/xmlcount_reward_func": -0.2852500081062317,
1029
+ "step": 60
1030
+ },
1031
+ {
1032
+ "completion_length": 197.75,
1033
+ "epoch": 0.000632931093518163,
1034
+ "grad_norm": 7.0625,
1035
+ "kl": 0.0004239616682752967,
1036
+ "learning_rate": 6.329113924050633e-08,
1037
+ "loss": 0.0,
1038
+ "reward": 3.9874868392944336,
1039
+ "reward_std": 0.3999238610267639,
1040
+ "rewards/combined_metrics_reward": 3.903986930847168,
1041
+ "rewards/reasoning_quality_reward": 0.37599998712539673,
1042
+ "rewards/soft_format_reward_func": 0.0,
1043
+ "rewards/strict_format_reward_func": 0.0,
1044
+ "rewards/xml_structure_reward": 0.0,
1045
+ "rewards/xmlcount_reward_func": -0.29249998927116394,
1046
+ "step": 61
1047
+ },
1048
+ {
1049
+ "completion_length": 359.625,
1050
+ "epoch": 0.0006433070130840346,
1051
+ "grad_norm": 4.09375,
1052
+ "kl": 0.0004899936029687524,
1053
+ "learning_rate": 6.432869890018676e-08,
1054
+ "loss": 0.0,
1055
+ "reward": 5.6926727294921875,
1056
+ "reward_std": 0.21776679158210754,
1057
+ "rewards/combined_metrics_reward": 6.028797149658203,
1058
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
1059
+ "rewards/soft_format_reward_func": 0.0,
1060
+ "rewards/strict_format_reward_func": 0.0,
1061
+ "rewards/xml_structure_reward": 0.0,
1062
+ "rewards/xmlcount_reward_func": -0.7361249923706055,
1063
+ "step": 62
1064
+ },
1065
+ {
1066
+ "completion_length": 321.125,
1067
+ "epoch": 0.0006536829326499061,
1068
+ "grad_norm": 4.1875,
1069
+ "kl": 0.00032837013714015484,
1070
+ "learning_rate": 6.536625855986719e-08,
1071
+ "loss": 0.0,
1072
+ "reward": 2.242539167404175,
1073
+ "reward_std": 0.3790563941001892,
1074
+ "rewards/combined_metrics_reward": 1.9982892274856567,
1075
+ "rewards/reasoning_quality_reward": 0.30000001192092896,
1076
+ "rewards/soft_format_reward_func": 0.0,
1077
+ "rewards/strict_format_reward_func": 0.0,
1078
+ "rewards/xml_structure_reward": 0.0,
1079
+ "rewards/xmlcount_reward_func": -0.055750008672475815,
1080
+ "step": 63
1081
+ },
1082
+ {
1083
+ "completion_length": 293.0,
1084
+ "epoch": 0.0006640588522157776,
1085
+ "grad_norm": 3.5,
1086
+ "kl": 0.0002956108655780554,
1087
+ "learning_rate": 6.640381821954764e-08,
1088
+ "loss": 0.0,
1089
+ "reward": 6.320035457611084,
1090
+ "reward_std": 0.37431028485298157,
1091
+ "rewards/combined_metrics_reward": 6.241035461425781,
1092
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
1093
+ "rewards/soft_format_reward_func": 0.0,
1094
+ "rewards/strict_format_reward_func": 0.0,
1095
+ "rewards/xml_structure_reward": 0.0,
1096
+ "rewards/xmlcount_reward_func": -0.32099997997283936,
1097
+ "step": 64
1098
+ },
1099
+ {
1100
+ "completion_length": 250.625,
1101
+ "epoch": 0.0006744347717816491,
1102
+ "grad_norm": 4.75,
1103
+ "kl": 0.0003711242461577058,
1104
+ "learning_rate": 6.744137787922807e-08,
1105
+ "loss": 0.0,
1106
+ "reward": 4.790735721588135,
1107
+ "reward_std": 0.2800223231315613,
1108
+ "rewards/combined_metrics_reward": 4.499361038208008,
1109
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
1110
+ "rewards/soft_format_reward_func": 0.0,
1111
+ "rewards/strict_format_reward_func": 0.0,
1112
+ "rewards/xml_structure_reward": 0.0,
1113
+ "rewards/xmlcount_reward_func": -0.10862499475479126,
1114
+ "step": 65
1115
+ },
1116
+ {
1117
+ "completion_length": 254.75,
1118
+ "epoch": 0.0006848106913475207,
1119
+ "grad_norm": 5.46875,
1120
+ "kl": 0.00045554860844276845,
1121
+ "learning_rate": 6.84789375389085e-08,
1122
+ "loss": 0.0,
1123
+ "reward": 5.346500873565674,
1124
+ "reward_std": 0.35901758074760437,
1125
+ "rewards/combined_metrics_reward": 5.343376159667969,
1126
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
1127
+ "rewards/soft_format_reward_func": 0.0,
1128
+ "rewards/strict_format_reward_func": 0.0,
1129
+ "rewards/xml_structure_reward": 0.0,
1130
+ "rewards/xmlcount_reward_func": -0.3968750238418579,
1131
+ "step": 66
1132
+ },
1133
+ {
1134
+ "completion_length": 355.0,
1135
+ "epoch": 0.0006951866109133922,
1136
+ "grad_norm": 4.5,
1137
+ "kl": 0.00045267416862770915,
1138
+ "learning_rate": 6.951649719858893e-08,
1139
+ "loss": 0.0,
1140
+ "reward": 4.087975978851318,
1141
+ "reward_std": 0.42723730206489563,
1142
+ "rewards/combined_metrics_reward": 4.250600814819336,
1143
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
1144
+ "rewards/soft_format_reward_func": 0.0,
1145
+ "rewards/strict_format_reward_func": 0.0,
1146
+ "rewards/xml_structure_reward": 0.0,
1147
+ "rewards/xmlcount_reward_func": -0.5626250505447388,
1148
+ "step": 67
1149
+ },
1150
+ {
1151
+ "completion_length": 407.875,
1152
+ "epoch": 0.0007055625304792637,
1153
+ "grad_norm": 4.3125,
1154
+ "kl": 0.0004084141692146659,
1155
+ "learning_rate": 7.055405685826936e-08,
1156
+ "loss": 0.0,
1157
+ "reward": 3.5405843257904053,
1158
+ "reward_std": 0.4435043931007385,
1159
+ "rewards/combined_metrics_reward": 4.00633430480957,
1160
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
1161
+ "rewards/soft_format_reward_func": 0.0,
1162
+ "rewards/strict_format_reward_func": 0.0,
1163
+ "rewards/xml_structure_reward": 0.0,
1164
+ "rewards/xmlcount_reward_func": -0.8657499551773071,
1165
+ "step": 68
1166
+ },
1167
+ {
1168
+ "completion_length": 334.75,
1169
+ "epoch": 0.0007159384500451352,
1170
+ "grad_norm": 4.4375,
1171
+ "kl": 0.0004419021715875715,
1172
+ "learning_rate": 7.159161651794979e-08,
1173
+ "loss": 0.0,
1174
+ "reward": 3.465590000152588,
1175
+ "reward_std": 0.5534517765045166,
1176
+ "rewards/combined_metrics_reward": 3.4629650115966797,
1177
+ "rewards/reasoning_quality_reward": 0.3499999940395355,
1178
+ "rewards/soft_format_reward_func": 0.0,
1179
+ "rewards/strict_format_reward_func": 0.0,
1180
+ "rewards/xml_structure_reward": 0.0,
1181
+ "rewards/xmlcount_reward_func": -0.3473750054836273,
1182
+ "step": 69
1183
+ },
1184
+ {
1185
+ "completion_length": 358.375,
1186
+ "epoch": 0.0007263143696110068,
1187
+ "grad_norm": 3.8125,
1188
+ "kl": 0.0004630927287507802,
1189
+ "learning_rate": 7.262917617763022e-08,
1190
+ "loss": 0.0,
1191
+ "reward": 2.3772149085998535,
1192
+ "reward_std": 0.5227242112159729,
1193
+ "rewards/combined_metrics_reward": 2.4412147998809814,
1194
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
1195
+ "rewards/soft_format_reward_func": 0.0,
1196
+ "rewards/strict_format_reward_func": 0.0,
1197
+ "rewards/xml_structure_reward": 0.0,
1198
+ "rewards/xmlcount_reward_func": -0.46399998664855957,
1199
+ "step": 70
1200
+ },
1201
+ {
1202
+ "completion_length": 311.625,
1203
+ "epoch": 0.0007366902891768783,
1204
+ "grad_norm": 4.71875,
1205
+ "kl": 0.00040126868407242,
1206
+ "learning_rate": 7.366673583731065e-08,
1207
+ "loss": 0.0,
1208
+ "reward": 6.1942291259765625,
1209
+ "reward_std": 0.4917367696762085,
1210
+ "rewards/combined_metrics_reward": 6.176229000091553,
1211
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
1212
+ "rewards/soft_format_reward_func": 0.0,
1213
+ "rewards/strict_format_reward_func": 0.0,
1214
+ "rewards/xml_structure_reward": 0.0,
1215
+ "rewards/xmlcount_reward_func": -0.38199999928474426,
1216
+ "step": 71
1217
+ },
1218
+ {
1219
+ "completion_length": 246.625,
1220
+ "epoch": 0.0007470662087427499,
1221
+ "grad_norm": 8.125,
1222
+ "kl": 0.00047063262900337577,
1223
+ "learning_rate": 7.470429549699109e-08,
1224
+ "loss": 0.0,
1225
+ "reward": 4.591141223907471,
1226
+ "reward_std": 0.3316625952720642,
1227
+ "rewards/combined_metrics_reward": 4.686141014099121,
1228
+ "rewards/reasoning_quality_reward": 0.37599998712539673,
1229
+ "rewards/soft_format_reward_func": 0.0,
1230
+ "rewards/strict_format_reward_func": 0.0,
1231
+ "rewards/xml_structure_reward": 0.0,
1232
+ "rewards/xmlcount_reward_func": -0.4710000157356262,
1233
+ "step": 72
1234
+ },
1235
+ {
1236
+ "completion_length": 301.375,
1237
+ "epoch": 0.0007574421283086213,
1238
+ "grad_norm": 4.03125,
1239
+ "kl": 0.0003384718729648739,
1240
+ "learning_rate": 7.574185515667152e-08,
1241
+ "loss": 0.0,
1242
+ "reward": 4.034180164337158,
1243
+ "reward_std": 0.4581345319747925,
1244
+ "rewards/combined_metrics_reward": 3.936805009841919,
1245
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
1246
+ "rewards/soft_format_reward_func": 0.0,
1247
+ "rewards/strict_format_reward_func": 0.0,
1248
+ "rewards/xml_structure_reward": 0.0,
1249
+ "rewards/xmlcount_reward_func": -0.30262500047683716,
1250
+ "step": 73
1251
+ },
1252
+ {
1253
+ "completion_length": 246.25,
1254
+ "epoch": 0.0007678180478744929,
1255
+ "grad_norm": 5.8125,
1256
+ "kl": 0.00038116276846267283,
1257
+ "learning_rate": 7.677941481635195e-08,
1258
+ "loss": 0.0,
1259
+ "reward": 4.223911285400391,
1260
+ "reward_std": 0.3177854120731354,
1261
+ "rewards/combined_metrics_reward": 3.9769115447998047,
1262
+ "rewards/reasoning_quality_reward": 0.38199999928474426,
1263
+ "rewards/soft_format_reward_func": 0.0,
1264
+ "rewards/strict_format_reward_func": 0.0,
1265
+ "rewards/xml_structure_reward": 0.0,
1266
+ "rewards/xmlcount_reward_func": -0.13500000536441803,
1267
+ "step": 74
1268
+ },
1269
+ {
1270
+ "completion_length": 357.0,
1271
+ "epoch": 0.0007781939674403644,
1272
+ "grad_norm": 3.96875,
1273
+ "kl": 0.0004593041376210749,
1274
+ "learning_rate": 7.781697447603238e-08,
1275
+ "loss": 0.0,
1276
+ "reward": 3.2472734451293945,
1277
+ "reward_std": 0.36452749371528625,
1278
+ "rewards/combined_metrics_reward": 3.1601481437683105,
1279
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
1280
+ "rewards/soft_format_reward_func": 0.0,
1281
+ "rewards/strict_format_reward_func": 0.0,
1282
+ "rewards/xml_structure_reward": 0.0,
1283
+ "rewards/xmlcount_reward_func": -0.312874972820282,
1284
+ "step": 75
1285
+ },
1286
+ {
1287
+ "completion_length": 333.75,
1288
+ "epoch": 0.000788569887006236,
1289
+ "grad_norm": 4.5,
1290
+ "kl": 0.000414425041526556,
1291
+ "learning_rate": 7.885453413571281e-08,
1292
+ "loss": 0.0,
1293
+ "reward": 4.1199727058410645,
1294
+ "reward_std": 0.4524296522140503,
1295
+ "rewards/combined_metrics_reward": 3.9803473949432373,
1296
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
1297
+ "rewards/soft_format_reward_func": 0.0,
1298
+ "rewards/strict_format_reward_func": 0.0,
1299
+ "rewards/xml_structure_reward": 0.0,
1300
+ "rewards/xmlcount_reward_func": -0.2603749930858612,
1301
+ "step": 76
1302
+ },
1303
+ {
1304
+ "completion_length": 312.875,
1305
+ "epoch": 0.0007989458065721074,
1306
+ "grad_norm": 4.9375,
1307
+ "kl": 0.000363428785931319,
1308
+ "learning_rate": 7.989209379539324e-08,
1309
+ "loss": 0.0,
1310
+ "reward": 3.9469006061553955,
1311
+ "reward_std": 0.3285008668899536,
1312
+ "rewards/combined_metrics_reward": 3.9924004077911377,
1313
+ "rewards/reasoning_quality_reward": 0.3930000066757202,
1314
+ "rewards/soft_format_reward_func": 0.0,
1315
+ "rewards/strict_format_reward_func": 0.0,
1316
+ "rewards/xml_structure_reward": 0.0,
1317
+ "rewards/xmlcount_reward_func": -0.43849998712539673,
1318
+ "step": 77
1319
+ },
1320
+ {
1321
+ "completion_length": 386.0,
1322
+ "epoch": 0.000809321726137979,
1323
+ "grad_norm": 4.75,
1324
+ "kl": 0.0005590686341747642,
1325
+ "learning_rate": 8.092965345507367e-08,
1326
+ "loss": 0.0,
1327
+ "reward": 4.085389137268066,
1328
+ "reward_std": 0.6028788089752197,
1329
+ "rewards/combined_metrics_reward": 4.339138984680176,
1330
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
1331
+ "rewards/soft_format_reward_func": 0.0,
1332
+ "rewards/strict_format_reward_func": 0.0,
1333
+ "rewards/xml_structure_reward": 0.0,
1334
+ "rewards/xmlcount_reward_func": -0.6537500023841858,
1335
+ "step": 78
1336
+ },
1337
+ {
1338
+ "completion_length": 288.125,
1339
+ "epoch": 0.0008196976457038505,
1340
+ "grad_norm": 4.46875,
1341
+ "kl": 0.0003678099310491234,
1342
+ "learning_rate": 8.19672131147541e-08,
1343
+ "loss": -0.0,
1344
+ "reward": 5.6469197273254395,
1345
+ "reward_std": 0.1786252111196518,
1346
+ "rewards/combined_metrics_reward": 5.719794750213623,
1347
+ "rewards/reasoning_quality_reward": 0.3499999940395355,
1348
+ "rewards/soft_format_reward_func": 0.0,
1349
+ "rewards/strict_format_reward_func": 0.0,
1350
+ "rewards/xml_structure_reward": 0.0,
1351
+ "rewards/xmlcount_reward_func": -0.42287498712539673,
1352
+ "step": 79
1353
+ },
1354
+ {
1355
+ "completion_length": 326.875,
1356
+ "epoch": 0.0008300735652697221,
1357
+ "grad_norm": 5.0625,
1358
+ "kl": 0.00044053790043108165,
1359
+ "learning_rate": 8.300477277443454e-08,
1360
+ "loss": 0.0,
1361
+ "reward": 2.7486777305603027,
1362
+ "reward_std": 0.4839881956577301,
1363
+ "rewards/combined_metrics_reward": 2.8931775093078613,
1364
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
1365
+ "rewards/soft_format_reward_func": 0.0,
1366
+ "rewards/strict_format_reward_func": 0.0,
1367
+ "rewards/xml_structure_reward": 0.0,
1368
+ "rewards/xmlcount_reward_func": -0.5444999933242798,
1369
+ "step": 80
1370
+ },
1371
+ {
1372
+ "completion_length": 302.125,
1373
+ "epoch": 0.0008404494848355936,
1374
+ "grad_norm": 4.96875,
1375
+ "kl": 0.00043243655818514526,
1376
+ "learning_rate": 8.404233243411497e-08,
1377
+ "loss": 0.0,
1378
+ "reward": 5.313750267028809,
1379
+ "reward_std": 0.2861633896827698,
1380
+ "rewards/combined_metrics_reward": 5.483749866485596,
1381
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
1382
+ "rewards/soft_format_reward_func": 0.0,
1383
+ "rewards/strict_format_reward_func": 0.0,
1384
+ "rewards/xml_structure_reward": 0.0,
1385
+ "rewards/xmlcount_reward_func": -0.5699999928474426,
1386
+ "step": 81
1387
+ },
1388
+ {
1389
+ "completion_length": 258.875,
1390
+ "epoch": 0.000850825404401465,
1391
+ "grad_norm": 4.78125,
1392
+ "kl": 0.0004002254572696984,
1393
+ "learning_rate": 8.50798920937954e-08,
1394
+ "loss": 0.0,
1395
+ "reward": 6.51301383972168,
1396
+ "reward_std": 0.3189328610897064,
1397
+ "rewards/combined_metrics_reward": 6.427763938903809,
1398
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
1399
+ "rewards/soft_format_reward_func": 0.0,
1400
+ "rewards/strict_format_reward_func": 0.0,
1401
+ "rewards/xml_structure_reward": 0.0,
1402
+ "rewards/xmlcount_reward_func": -0.3147500157356262,
1403
+ "step": 82
1404
+ },
1405
+ {
1406
+ "completion_length": 309.125,
1407
+ "epoch": 0.0008612013239673366,
1408
+ "grad_norm": 3.953125,
1409
+ "kl": 0.00043886929051950574,
1410
+ "learning_rate": 8.611745175347583e-08,
1411
+ "loss": 0.0,
1412
+ "reward": 5.597060680389404,
1413
+ "reward_std": 0.2558835446834564,
1414
+ "rewards/combined_metrics_reward": 5.714810371398926,
1415
+ "rewards/reasoning_quality_reward": 0.3500000238418579,
1416
+ "rewards/soft_format_reward_func": 0.0,
1417
+ "rewards/strict_format_reward_func": 0.0,
1418
+ "rewards/xml_structure_reward": 0.0,
1419
+ "rewards/xmlcount_reward_func": -0.46775001287460327,
1420
+ "step": 83
1421
+ },
1422
+ {
1423
+ "completion_length": 321.5,
1424
+ "epoch": 0.0008715772435332081,
1425
+ "grad_norm": 4.1875,
1426
+ "kl": 0.0004138578078709543,
1427
+ "learning_rate": 8.715501141315627e-08,
1428
+ "loss": 0.0,
1429
+ "reward": 3.8980519771575928,
1430
+ "reward_std": 0.7407993078231812,
1431
+ "rewards/combined_metrics_reward": 3.937551975250244,
1432
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
1433
+ "rewards/soft_format_reward_func": 0.0,
1434
+ "rewards/strict_format_reward_func": 0.0,
1435
+ "rewards/xml_structure_reward": 0.0,
1436
+ "rewards/xmlcount_reward_func": -0.43950003385543823,
1437
+ "step": 84
1438
+ },
1439
+ {
1440
+ "completion_length": 393.875,
1441
+ "epoch": 0.0008819531630990797,
1442
+ "grad_norm": 3.6875,
1443
+ "kl": 0.000397436844650656,
1444
+ "learning_rate": 8.819257107283669e-08,
1445
+ "loss": 0.0,
1446
+ "reward": 2.608250617980957,
1447
+ "reward_std": 0.8483739495277405,
1448
+ "rewards/combined_metrics_reward": 2.669625759124756,
1449
+ "rewards/reasoning_quality_reward": 0.38600000739097595,
1450
+ "rewards/soft_format_reward_func": 0.0,
1451
+ "rewards/strict_format_reward_func": 0.0,
1452
+ "rewards/xml_structure_reward": 0.0,
1453
+ "rewards/xmlcount_reward_func": -0.44737496972084045,
1454
+ "step": 85
1455
+ },
1456
+ {
1457
+ "completion_length": 277.125,
1458
+ "epoch": 0.0008923290826649511,
1459
+ "grad_norm": 4.5625,
1460
+ "kl": 0.0003580040065571666,
1461
+ "learning_rate": 8.923013073251713e-08,
1462
+ "loss": 0.0,
1463
+ "reward": 6.172883033752441,
1464
+ "reward_std": 0.3094210624694824,
1465
+ "rewards/combined_metrics_reward": 6.0756330490112305,
1466
+ "rewards/reasoning_quality_reward": 0.3930000066757202,
1467
+ "rewards/soft_format_reward_func": 0.0,
1468
+ "rewards/strict_format_reward_func": 0.0,
1469
+ "rewards/xml_structure_reward": 0.0,
1470
+ "rewards/xmlcount_reward_func": -0.2957499921321869,
1471
+ "step": 86
1472
+ },
1473
+ {
1474
+ "completion_length": 280.0,
1475
+ "epoch": 0.0009027050022308227,
1476
+ "grad_norm": 5.46875,
1477
+ "kl": 0.0004139384545851499,
1478
+ "learning_rate": 9.026769039219755e-08,
1479
+ "loss": -0.0,
1480
+ "reward": 5.4773406982421875,
1481
+ "reward_std": 0.23652179539203644,
1482
+ "rewards/combined_metrics_reward": 5.410591125488281,
1483
+ "rewards/reasoning_quality_reward": 0.28700000047683716,
1484
+ "rewards/soft_format_reward_func": 0.0,
1485
+ "rewards/strict_format_reward_func": 0.0,
1486
+ "rewards/xml_structure_reward": 0.0,
1487
+ "rewards/xmlcount_reward_func": -0.2202499955892563,
1488
+ "step": 87
1489
+ },
1490
+ {
1491
+ "completion_length": 265.625,
1492
+ "epoch": 0.0009130809217966942,
1493
+ "grad_norm": 4.9375,
1494
+ "kl": 0.00047231599455699325,
1495
+ "learning_rate": 9.130525005187799e-08,
1496
+ "loss": -0.0,
1497
+ "reward": 4.649065017700195,
1498
+ "reward_std": 0.33985596895217896,
1499
+ "rewards/combined_metrics_reward": 4.465190410614014,
1500
+ "rewards/reasoning_quality_reward": 0.3499999940395355,
1501
+ "rewards/soft_format_reward_func": 0.0,
1502
+ "rewards/strict_format_reward_func": 0.0,
1503
+ "rewards/xml_structure_reward": 0.0,
1504
+ "rewards/xmlcount_reward_func": -0.16612499952316284,
1505
+ "step": 88
1506
+ },
1507
+ {
1508
+ "completion_length": 378.75,
1509
+ "epoch": 0.0009234568413625658,
1510
+ "grad_norm": 3.65625,
1511
+ "kl": 0.0003876351984217763,
1512
+ "learning_rate": 9.234280971155841e-08,
1513
+ "loss": 0.0,
1514
+ "reward": 2.551896572113037,
1515
+ "reward_std": 0.5467392206192017,
1516
+ "rewards/combined_metrics_reward": 2.5751466751098633,
1517
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
1518
+ "rewards/soft_format_reward_func": 0.0,
1519
+ "rewards/strict_format_reward_func": 0.0,
1520
+ "rewards/xml_structure_reward": 0.0,
1521
+ "rewards/xmlcount_reward_func": -0.4232499897480011,
1522
+ "step": 89
1523
+ },
1524
+ {
1525
+ "completion_length": 424.0,
1526
+ "epoch": 0.0009338327609284372,
1527
+ "grad_norm": 4.625,
1528
+ "kl": 0.0003842959995381534,
1529
+ "learning_rate": 9.338036937123885e-08,
1530
+ "loss": 0.0,
1531
+ "reward": 3.5671541690826416,
1532
+ "reward_std": 0.48063141107559204,
1533
+ "rewards/combined_metrics_reward": 3.762529134750366,
1534
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
1535
+ "rewards/soft_format_reward_func": 0.0,
1536
+ "rewards/strict_format_reward_func": 0.0,
1537
+ "rewards/xml_structure_reward": 0.0,
1538
+ "rewards/xmlcount_reward_func": -0.5953750014305115,
1539
+ "step": 90
1540
+ },
1541
+ {
1542
+ "completion_length": 289.625,
1543
+ "epoch": 0.0009442086804943088,
1544
+ "grad_norm": 4.84375,
1545
+ "kl": 0.0004389020032249391,
1546
+ "learning_rate": 9.44179290309193e-08,
1547
+ "loss": 0.0,
1548
+ "reward": 5.862105369567871,
1549
+ "reward_std": 0.39258119463920593,
1550
+ "rewards/combined_metrics_reward": 5.712730407714844,
1551
+ "rewards/reasoning_quality_reward": 0.30000001192092896,
1552
+ "rewards/soft_format_reward_func": 0.0,
1553
+ "rewards/strict_format_reward_func": 0.0,
1554
+ "rewards/xml_structure_reward": 0.0,
1555
+ "rewards/xmlcount_reward_func": -0.15062500536441803,
1556
+ "step": 91
1557
+ },
1558
+ {
1559
+ "completion_length": 350.125,
1560
+ "epoch": 0.0009545846000601803,
1561
+ "grad_norm": 5.03125,
1562
+ "kl": 0.0005457468214444816,
1563
+ "learning_rate": 9.545548869059971e-08,
1564
+ "loss": 0.0,
1565
+ "reward": 4.453487396240234,
1566
+ "reward_std": 0.5325824618339539,
1567
+ "rewards/combined_metrics_reward": 4.3758625984191895,
1568
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
1569
+ "rewards/soft_format_reward_func": 0.0,
1570
+ "rewards/strict_format_reward_func": 0.0,
1571
+ "rewards/xml_structure_reward": 0.0,
1572
+ "rewards/xmlcount_reward_func": -0.32237499952316284,
1573
+ "step": 92
1574
+ },
1575
+ {
1576
+ "completion_length": 371.0,
1577
+ "epoch": 0.0009649605196260519,
1578
+ "grad_norm": 3.6875,
1579
+ "kl": 0.00036559661384671926,
1580
+ "learning_rate": 9.649304835028016e-08,
1581
+ "loss": 0.0,
1582
+ "reward": 3.771514415740967,
1583
+ "reward_std": 0.28220006823539734,
1584
+ "rewards/combined_metrics_reward": 3.834014415740967,
1585
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
1586
+ "rewards/soft_format_reward_func": 0.0,
1587
+ "rewards/strict_format_reward_func": 0.0,
1588
+ "rewards/xml_structure_reward": 0.0,
1589
+ "rewards/xmlcount_reward_func": -0.46250003576278687,
1590
+ "step": 93
1591
+ },
1592
+ {
1593
+ "completion_length": 274.375,
1594
+ "epoch": 0.0009753364391919234,
1595
+ "grad_norm": 4.40625,
1596
+ "kl": 0.0004123499966226518,
1597
+ "learning_rate": 9.753060800996057e-08,
1598
+ "loss": 0.0,
1599
+ "reward": 2.0246853828430176,
1600
+ "reward_std": 0.41562631726264954,
1601
+ "rewards/combined_metrics_reward": 1.9075604677200317,
1602
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
1603
+ "rewards/soft_format_reward_func": 0.0,
1604
+ "rewards/strict_format_reward_func": 0.0,
1605
+ "rewards/xml_structure_reward": 0.0,
1606
+ "rewards/xmlcount_reward_func": -0.2828750014305115,
1607
+ "step": 94
1608
+ },
1609
+ {
1610
+ "completion_length": 293.25,
1611
+ "epoch": 0.0009857123587577949,
1612
+ "grad_norm": 4.1875,
1613
+ "kl": 0.0003433750825934112,
1614
+ "learning_rate": 9.856816766964102e-08,
1615
+ "loss": 0.0,
1616
+ "reward": 3.7557971477508545,
1617
+ "reward_std": 0.37939074635505676,
1618
+ "rewards/combined_metrics_reward": 3.5406720638275146,
1619
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
1620
+ "rewards/soft_format_reward_func": 0.0,
1621
+ "rewards/strict_format_reward_func": 0.0,
1622
+ "rewards/xml_structure_reward": 0.0,
1623
+ "rewards/xmlcount_reward_func": -0.1848750114440918,
1624
+ "step": 95
1625
+ },
1626
+ {
1627
+ "completion_length": 425.25,
1628
+ "epoch": 0.0009960882783236664,
1629
+ "grad_norm": 3.25,
1630
+ "kl": 0.00045561580918729305,
1631
+ "learning_rate": 9.960572732932143e-08,
1632
+ "loss": 0.0,
1633
+ "reward": 2.278918981552124,
1634
+ "reward_std": 0.49236196279525757,
1635
+ "rewards/combined_metrics_reward": 2.591418981552124,
1636
+ "rewards/reasoning_quality_reward": 0.3500000238418579,
1637
+ "rewards/soft_format_reward_func": 0.0,
1638
+ "rewards/strict_format_reward_func": 0.0,
1639
+ "rewards/xml_structure_reward": 0.0,
1640
+ "rewards/xmlcount_reward_func": -0.6624999642372131,
1641
+ "step": 96
1642
+ },
1643
+ {
1644
+ "completion_length": 291.25,
1645
+ "epoch": 0.001006464197889538,
1646
+ "grad_norm": 4.0625,
1647
+ "kl": 0.0003741452528629452,
1648
+ "learning_rate": 1.0064328698900188e-07,
1649
+ "loss": -0.0,
1650
+ "reward": 4.669227600097656,
1651
+ "reward_std": 0.15019282698631287,
1652
+ "rewards/combined_metrics_reward": 4.414227485656738,
1653
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
1654
+ "rewards/soft_format_reward_func": 0.0,
1655
+ "rewards/strict_format_reward_func": 0.0,
1656
+ "rewards/xml_structure_reward": 0.0,
1657
+ "rewards/xmlcount_reward_func": -0.14499999582767487,
1658
+ "step": 97
1659
+ },
1660
+ {
1661
+ "completion_length": 286.75,
1662
+ "epoch": 0.0010168401174554095,
1663
+ "grad_norm": 4.53125,
1664
+ "kl": 0.00041974103078246117,
1665
+ "learning_rate": 1.0168084664868232e-07,
1666
+ "loss": 0.0,
1667
+ "reward": 5.2955803871154785,
1668
+ "reward_std": 0.38848426938056946,
1669
+ "rewards/combined_metrics_reward": 5.220705509185791,
1670
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
1671
+ "rewards/soft_format_reward_func": 0.0,
1672
+ "rewards/strict_format_reward_func": 0.0,
1673
+ "rewards/xml_structure_reward": 0.0,
1674
+ "rewards/xmlcount_reward_func": -0.32512497901916504,
1675
+ "step": 98
1676
+ },
1677
+ {
1678
+ "completion_length": 217.75,
1679
+ "epoch": 0.001027216037021281,
1680
+ "grad_norm": 4.71875,
1681
+ "kl": 0.00041393833816982806,
1682
+ "learning_rate": 1.0271840630836274e-07,
1683
+ "loss": 0.0,
1684
+ "reward": 6.190217018127441,
1685
+ "reward_std": 0.4344483017921448,
1686
+ "rewards/combined_metrics_reward": 6.11096715927124,
1687
+ "rewards/reasoning_quality_reward": 0.3879999816417694,
1688
+ "rewards/soft_format_reward_func": 0.0,
1689
+ "rewards/strict_format_reward_func": 0.0,
1690
+ "rewards/xml_structure_reward": 0.0,
1691
+ "rewards/xmlcount_reward_func": -0.3087499737739563,
1692
+ "step": 99
1693
+ },
1694
+ {
1695
+ "completion_length": 373.625,
1696
+ "epoch": 0.0010375919565871526,
1697
+ "grad_norm": 3.546875,
1698
+ "kl": 0.000364527601050213,
1699
+ "learning_rate": 1.0375596596804318e-07,
1700
+ "loss": 0.0,
1701
+ "reward": 2.4266605377197266,
1702
+ "reward_std": 0.5906604528427124,
1703
+ "rewards/combined_metrics_reward": 2.5370354652404785,
1704
+ "rewards/reasoning_quality_reward": 0.4000000059604645,
1705
+ "rewards/soft_format_reward_func": 0.0,
1706
+ "rewards/strict_format_reward_func": 0.0,
1707
+ "rewards/xml_structure_reward": 0.0,
1708
+ "rewards/xmlcount_reward_func": -0.5103750228881836,
1709
+ "step": 100
1710
+ }
1711
+ ],
1712
+ "logging_steps": 1,
1713
+ "max_steps": 96377,
1714
+ "num_input_tokens_seen": 0,
1715
+ "num_train_epochs": 1,
1716
+ "save_steps": 100,
1717
+ "stateful_callbacks": {
1718
+ "TrainerControl": {
1719
+ "args": {
1720
+ "should_epoch_stop": false,
1721
+ "should_evaluate": false,
1722
+ "should_log": false,
1723
+ "should_save": true,
1724
+ "should_training_stop": false
1725
+ },
1726
+ "attributes": {}
1727
+ }
1728
+ },
1729
+ "total_flos": 0.0,
1730
+ "train_batch_size": 1,
1731
+ "trial_name": null,
1732
+ "trial_params": null
1733
+ }
Llama-3.2-3B-GRPO-Indic-v1/checkpoint-100/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61c6a784321e3130e4247d1a1492d5e5186962451ddf5055e78be88705c93bf4
3
+ size 5624
Qwen2.5-1.5B-GRPO-Indic-v1/checkpoint-100/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
Qwen2.5-1.5B-GRPO-Indic-v1/checkpoint-100/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 1536,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 8960,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 21,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 28,
18
+ "num_key_value_heads": 2,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_scaling": null,
21
+ "rope_theta": 1000000.0,
22
+ "sliding_window": null,
23
+ "tie_word_embeddings": true,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.48.2",
26
+ "use_cache": true,
27
+ "use_sliding_window": false,
28
+ "vocab_size": 151936
29
+ }
Qwen2.5-1.5B-GRPO-Indic-v1/checkpoint-100/generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.1,
10
+ "temperature": 0.7,
11
+ "top_k": 20,
12
+ "top_p": 0.8,
13
+ "transformers_version": "4.48.2"
14
+ }
Qwen2.5-1.5B-GRPO-Indic-v1/checkpoint-100/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
Qwen2.5-1.5B-GRPO-Indic-v1/checkpoint-100/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c9e178ddfa86060db651ae25bcc1b93bdae00f4806b6640e03832695cb85e21
3
+ size 3087467144
Qwen2.5-1.5B-GRPO-Indic-v1/checkpoint-100/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e036c7ca2c498fc11469607556fd363ca825d170be41d58b3c121c7c0ef14001
3
+ size 6175147196
Qwen2.5-1.5B-GRPO-Indic-v1/checkpoint-100/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:484a771dcbe93b8a8014a8230e4a25196556ca4181c555c8622228bc0061d6ca
3
+ size 14512
Qwen2.5-1.5B-GRPO-Indic-v1/checkpoint-100/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a555260bee4f1da759e46e2624c393c4733329f55d9ac1dcde2d8c9291d6c51
3
+ size 14512
Qwen2.5-1.5B-GRPO-Indic-v1/checkpoint-100/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8877303b05b0057de2ea5bba61df7da797759c06c8fac5099101c80d132c2920
3
+ size 1064
Qwen2.5-1.5B-GRPO-Indic-v1/checkpoint-100/special_tokens_map.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": "<|im_end|>"
25
+ }
Qwen2.5-1.5B-GRPO-Indic-v1/checkpoint-100/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63a2951d5edfa5cc0a2346ef872f8c77a2920274cfc3b503b04e3799104dee80
3
+ size 11422060
Qwen2.5-1.5B-GRPO-Indic-v1/checkpoint-100/tokenizer_config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|im_end|>",
201
+ "errors": "replace",
202
+ "extra_special_tokens": {},
203
+ "model_max_length": 131072,
204
+ "pad_token": "<|im_end|>",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
Qwen2.5-1.5B-GRPO-Indic-v1/checkpoint-100/trainer_state.json ADDED
@@ -0,0 +1,1733 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.0020751839131743052,
5
+ "eval_steps": 500,
6
+ "global_step": 100,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "completion_length": 217.9375,
13
+ "epoch": 2.075183913174305e-05,
14
+ "grad_norm": 5.71875,
15
+ "kl": 0.0,
16
+ "learning_rate": 2.0751193193608636e-09,
17
+ "loss": -0.0,
18
+ "reward": 2.1214839816093445,
19
+ "reward_std": 0.3205597698688507,
20
+ "rewards/combined_metrics_reward": 1.6968590021133423,
21
+ "rewards/reasoning_quality_reward": 0.3189999908208847,
22
+ "rewards/soft_format_reward_func": 0.0,
23
+ "rewards/strict_format_reward_func": 0.0,
24
+ "rewards/xml_structure_reward": 0.0,
25
+ "rewards/xmlcount_reward_func": 0.10562500357627869,
26
+ "step": 1
27
+ },
28
+ {
29
+ "completion_length": 201.6875,
30
+ "epoch": 4.15036782634861e-05,
31
+ "grad_norm": 4.3125,
32
+ "kl": 0.0,
33
+ "learning_rate": 4.150238638721727e-09,
34
+ "loss": 0.0,
35
+ "reward": 2.7721004486083984,
36
+ "reward_std": 0.2828262448310852,
37
+ "rewards/combined_metrics_reward": 2.395788013935089,
38
+ "rewards/reasoning_quality_reward": 0.2459999918937683,
39
+ "rewards/soft_format_reward_func": 0.0,
40
+ "rewards/strict_format_reward_func": 0.0,
41
+ "rewards/xml_structure_reward": 0.0,
42
+ "rewards/xmlcount_reward_func": 0.1303124986588955,
43
+ "step": 2
44
+ },
45
+ {
46
+ "completion_length": 192.125,
47
+ "epoch": 6.225551739522915e-05,
48
+ "grad_norm": 4.375,
49
+ "kl": 0.0007675105007365346,
50
+ "learning_rate": 6.22535795808259e-09,
51
+ "loss": 0.0,
52
+ "reward": 1.9744819402694702,
53
+ "reward_std": 0.24307005107402802,
54
+ "rewards/combined_metrics_reward": 1.5036693811416626,
55
+ "rewards/reasoning_quality_reward": 0.3264999985694885,
56
+ "rewards/soft_format_reward_func": 0.0,
57
+ "rewards/strict_format_reward_func": 0.0,
58
+ "rewards/xml_structure_reward": 0.0,
59
+ "rewards/xmlcount_reward_func": 0.14431249350309372,
60
+ "step": 3
61
+ },
62
+ {
63
+ "completion_length": 164.3125,
64
+ "epoch": 8.30073565269722e-05,
65
+ "grad_norm": 5.0,
66
+ "kl": 0.0008232884283643216,
67
+ "learning_rate": 8.300477277443455e-09,
68
+ "loss": 0.0,
69
+ "reward": 2.804524064064026,
70
+ "reward_std": 0.25351303815841675,
71
+ "rewards/combined_metrics_reward": 2.36052405834198,
72
+ "rewards/reasoning_quality_reward": 0.28599999845027924,
73
+ "rewards/soft_format_reward_func": 0.0,
74
+ "rewards/strict_format_reward_func": 0.0,
75
+ "rewards/xml_structure_reward": 0.0,
76
+ "rewards/xmlcount_reward_func": 0.15799999982118607,
77
+ "step": 4
78
+ },
79
+ {
80
+ "completion_length": 117.5,
81
+ "epoch": 0.00010375919565871526,
82
+ "grad_norm": 5.84375,
83
+ "kl": 0.000949281791690737,
84
+ "learning_rate": 1.0375596596804317e-08,
85
+ "loss": 0.0,
86
+ "reward": 3.938944101333618,
87
+ "reward_std": 0.286952406167984,
88
+ "rewards/combined_metrics_reward": 3.347694158554077,
89
+ "rewards/reasoning_quality_reward": 0.283500000834465,
90
+ "rewards/soft_format_reward_func": 0.0,
91
+ "rewards/strict_format_reward_func": 0.0,
92
+ "rewards/xml_structure_reward": 0.0,
93
+ "rewards/xmlcount_reward_func": 0.30774998664855957,
94
+ "step": 5
95
+ },
96
+ {
97
+ "completion_length": 151.875,
98
+ "epoch": 0.0001245110347904583,
99
+ "grad_norm": 5.03125,
100
+ "kl": 0.0008323155052494258,
101
+ "learning_rate": 1.245071591616518e-08,
102
+ "loss": 0.0,
103
+ "reward": 3.980774402618408,
104
+ "reward_std": 0.17779755592346191,
105
+ "rewards/combined_metrics_reward": 3.4332743883132935,
106
+ "rewards/reasoning_quality_reward": 0.3264999985694885,
107
+ "rewards/soft_format_reward_func": 0.0,
108
+ "rewards/strict_format_reward_func": 0.0,
109
+ "rewards/xml_structure_reward": 0.0,
110
+ "rewards/xmlcount_reward_func": 0.22099999338388443,
111
+ "step": 6
112
+ },
113
+ {
114
+ "completion_length": 133.5,
115
+ "epoch": 0.00014526287392220135,
116
+ "grad_norm": 7.34375,
117
+ "kl": 0.0009322284895461053,
118
+ "learning_rate": 1.4525835235526043e-08,
119
+ "loss": 0.0,
120
+ "reward": 5.339264154434204,
121
+ "reward_std": 0.286283515393734,
122
+ "rewards/combined_metrics_reward": 4.70457649230957,
123
+ "rewards/reasoning_quality_reward": 0.32750001549720764,
124
+ "rewards/soft_format_reward_func": 0.0,
125
+ "rewards/strict_format_reward_func": 0.0,
126
+ "rewards/xml_structure_reward": 0.0,
127
+ "rewards/xmlcount_reward_func": 0.3071874976158142,
128
+ "step": 7
129
+ },
130
+ {
131
+ "completion_length": 226.375,
132
+ "epoch": 0.0001660147130539444,
133
+ "grad_norm": 5.09375,
134
+ "kl": 0.0008909371099434793,
135
+ "learning_rate": 1.660095455488691e-08,
136
+ "loss": -0.0,
137
+ "reward": 4.727461576461792,
138
+ "reward_std": 0.2516580820083618,
139
+ "rewards/combined_metrics_reward": 4.169149160385132,
140
+ "rewards/reasoning_quality_reward": 0.328000009059906,
141
+ "rewards/soft_format_reward_func": 0.0,
142
+ "rewards/strict_format_reward_func": 0.0,
143
+ "rewards/xml_structure_reward": 0.0,
144
+ "rewards/xmlcount_reward_func": 0.2303125038743019,
145
+ "step": 8
146
+ },
147
+ {
148
+ "completion_length": 133.9375,
149
+ "epoch": 0.00018676655218568747,
150
+ "grad_norm": 5.375,
151
+ "kl": 0.0010912964353337884,
152
+ "learning_rate": 1.8676073874247773e-08,
153
+ "loss": 0.0,
154
+ "reward": 3.5169103145599365,
155
+ "reward_std": 0.25320689380168915,
156
+ "rewards/combined_metrics_reward": 2.942910313606262,
157
+ "rewards/reasoning_quality_reward": 0.3199999928474426,
158
+ "rewards/soft_format_reward_func": 0.0,
159
+ "rewards/strict_format_reward_func": 0.0,
160
+ "rewards/xml_structure_reward": 0.0,
161
+ "rewards/xmlcount_reward_func": 0.2539999857544899,
162
+ "step": 9
163
+ },
164
+ {
165
+ "completion_length": 244.0,
166
+ "epoch": 0.00020751839131743051,
167
+ "grad_norm": 4.3125,
168
+ "kl": 0.0009266288252547383,
169
+ "learning_rate": 2.0751193193608634e-08,
170
+ "loss": 0.0,
171
+ "reward": 2.775857090950012,
172
+ "reward_std": 0.3486485034227371,
173
+ "rewards/combined_metrics_reward": 2.23591947555542,
174
+ "rewards/reasoning_quality_reward": 0.3050000071525574,
175
+ "rewards/soft_format_reward_func": 0.0,
176
+ "rewards/strict_format_reward_func": 0.0,
177
+ "rewards/xml_structure_reward": 0.0,
178
+ "rewards/xmlcount_reward_func": 0.23493748903274536,
179
+ "step": 10
180
+ },
181
+ {
182
+ "completion_length": 213.0,
183
+ "epoch": 0.00022827023044917356,
184
+ "grad_norm": 4.75,
185
+ "kl": 0.0010399019811302423,
186
+ "learning_rate": 2.2826312512969498e-08,
187
+ "loss": 0.0,
188
+ "reward": 2.716602325439453,
189
+ "reward_std": 0.295271098613739,
190
+ "rewards/combined_metrics_reward": 2.376789927482605,
191
+ "rewards/reasoning_quality_reward": 0.1979999989271164,
192
+ "rewards/soft_format_reward_func": 0.0,
193
+ "rewards/strict_format_reward_func": 0.0,
194
+ "rewards/xml_structure_reward": 0.0,
195
+ "rewards/xmlcount_reward_func": 0.1418124958872795,
196
+ "step": 11
197
+ },
198
+ {
199
+ "completion_length": 200.8125,
200
+ "epoch": 0.0002490220695809166,
201
+ "grad_norm": 5.375,
202
+ "kl": 0.0008770620042923838,
203
+ "learning_rate": 2.490143183233036e-08,
204
+ "loss": 0.0,
205
+ "reward": 3.1651769876480103,
206
+ "reward_std": 0.23828785121440887,
207
+ "rewards/combined_metrics_reward": 2.7553645372390747,
208
+ "rewards/reasoning_quality_reward": 0.26749999821186066,
209
+ "rewards/soft_format_reward_func": 0.0,
210
+ "rewards/strict_format_reward_func": 0.0,
211
+ "rewards/xml_structure_reward": 0.0,
212
+ "rewards/xmlcount_reward_func": 0.14231250062584877,
213
+ "step": 12
214
+ },
215
+ {
216
+ "completion_length": 135.875,
217
+ "epoch": 0.00026977390871265965,
218
+ "grad_norm": 5.21875,
219
+ "kl": 0.0008087488822638988,
220
+ "learning_rate": 2.6976551151691226e-08,
221
+ "loss": 0.0,
222
+ "reward": 3.4093174934387207,
223
+ "reward_std": 0.18929830193519592,
224
+ "rewards/combined_metrics_reward": 2.7071924209594727,
225
+ "rewards/reasoning_quality_reward": 0.3475000113248825,
226
+ "rewards/soft_format_reward_func": 0.0,
227
+ "rewards/strict_format_reward_func": 0.0,
228
+ "rewards/xml_structure_reward": 0.0,
229
+ "rewards/xmlcount_reward_func": 0.35462500154972076,
230
+ "step": 13
231
+ },
232
+ {
233
+ "completion_length": 280.1875,
234
+ "epoch": 0.0002905257478444027,
235
+ "grad_norm": 4.125,
236
+ "kl": 0.0009126374206971377,
237
+ "learning_rate": 2.9051670471052087e-08,
238
+ "loss": -0.0,
239
+ "reward": 1.895992934703827,
240
+ "reward_std": 0.29027901589870453,
241
+ "rewards/combined_metrics_reward": 1.498617947101593,
242
+ "rewards/reasoning_quality_reward": 0.24199999868869781,
243
+ "rewards/soft_format_reward_func": 0.0,
244
+ "rewards/strict_format_reward_func": 0.0,
245
+ "rewards/xml_structure_reward": 0.0,
246
+ "rewards/xmlcount_reward_func": 0.15537499636411667,
247
+ "step": 14
248
+ },
249
+ {
250
+ "completion_length": 152.4375,
251
+ "epoch": 0.00031127758697614574,
252
+ "grad_norm": 5.3125,
253
+ "kl": 0.0009023483144119382,
254
+ "learning_rate": 3.112678979041295e-08,
255
+ "loss": 0.0,
256
+ "reward": 2.4294240474700928,
257
+ "reward_std": 0.3003406375646591,
258
+ "rewards/combined_metrics_reward": 1.922486662864685,
259
+ "rewards/reasoning_quality_reward": 0.30799999833106995,
260
+ "rewards/soft_format_reward_func": 0.0,
261
+ "rewards/strict_format_reward_func": 0.0,
262
+ "rewards/xml_structure_reward": 0.0,
263
+ "rewards/xmlcount_reward_func": 0.19893749803304672,
264
+ "step": 15
265
+ },
266
+ {
267
+ "completion_length": 171.0625,
268
+ "epoch": 0.0003320294261078888,
269
+ "grad_norm": 4.09375,
270
+ "kl": 0.0008525688899680972,
271
+ "learning_rate": 3.320190910977382e-08,
272
+ "loss": 0.0,
273
+ "reward": 2.5242298245429993,
274
+ "reward_std": 0.20701657980680466,
275
+ "rewards/combined_metrics_reward": 2.0051047801971436,
276
+ "rewards/reasoning_quality_reward": 0.31599999964237213,
277
+ "rewards/soft_format_reward_func": 0.0,
278
+ "rewards/strict_format_reward_func": 0.0,
279
+ "rewards/xml_structure_reward": 0.0,
280
+ "rewards/xmlcount_reward_func": 0.203125,
281
+ "step": 16
282
+ },
283
+ {
284
+ "completion_length": 151.625,
285
+ "epoch": 0.00035278126523963184,
286
+ "grad_norm": 5.5,
287
+ "kl": 0.0008518545655533671,
288
+ "learning_rate": 3.527702842913468e-08,
289
+ "loss": 0.0,
290
+ "reward": 2.9983707666397095,
291
+ "reward_std": 0.5795058161020279,
292
+ "rewards/combined_metrics_reward": 2.652183175086975,
293
+ "rewards/reasoning_quality_reward": 0.27699999511241913,
294
+ "rewards/soft_format_reward_func": 0.0,
295
+ "rewards/strict_format_reward_func": 0.0,
296
+ "rewards/xml_structure_reward": 0.0,
297
+ "rewards/xmlcount_reward_func": 0.06918748468160629,
298
+ "step": 17
299
+ },
300
+ {
301
+ "completion_length": 110.125,
302
+ "epoch": 0.00037353310437137494,
303
+ "grad_norm": 6.28125,
304
+ "kl": 0.000982005090918392,
305
+ "learning_rate": 3.7352147748495546e-08,
306
+ "loss": 0.0,
307
+ "reward": 4.563453435897827,
308
+ "reward_std": 0.38466793298721313,
309
+ "rewards/combined_metrics_reward": 3.9920783042907715,
310
+ "rewards/reasoning_quality_reward": 0.27550001442432404,
311
+ "rewards/soft_format_reward_func": 0.0,
312
+ "rewards/strict_format_reward_func": 0.0,
313
+ "rewards/xml_structure_reward": 0.0,
314
+ "rewards/xmlcount_reward_func": 0.2958749830722809,
315
+ "step": 18
316
+ },
317
+ {
318
+ "completion_length": 214.0625,
319
+ "epoch": 0.000394284943503118,
320
+ "grad_norm": 3.890625,
321
+ "kl": 0.0008488663588650525,
322
+ "learning_rate": 3.942726706785641e-08,
323
+ "loss": 0.0,
324
+ "reward": 2.592466711997986,
325
+ "reward_std": 0.21462315320968628,
326
+ "rewards/combined_metrics_reward": 2.1404041051864624,
327
+ "rewards/reasoning_quality_reward": 0.33800001442432404,
328
+ "rewards/soft_format_reward_func": 0.0,
329
+ "rewards/strict_format_reward_func": 0.0,
330
+ "rewards/xml_structure_reward": 0.0,
331
+ "rewards/xmlcount_reward_func": 0.11406249366700649,
332
+ "step": 19
333
+ },
334
+ {
335
+ "completion_length": 186.1875,
336
+ "epoch": 0.00041503678263486103,
337
+ "grad_norm": 4.15625,
338
+ "kl": 0.0009700933587737381,
339
+ "learning_rate": 4.150238638721727e-08,
340
+ "loss": 0.0,
341
+ "reward": 3.67450213432312,
342
+ "reward_std": 0.34302355349063873,
343
+ "rewards/combined_metrics_reward": 3.2374396324157715,
344
+ "rewards/reasoning_quality_reward": 0.31450000405311584,
345
+ "rewards/soft_format_reward_func": 0.0,
346
+ "rewards/strict_format_reward_func": 0.0,
347
+ "rewards/xml_structure_reward": 0.0,
348
+ "rewards/xmlcount_reward_func": 0.12256250530481339,
349
+ "step": 20
350
+ },
351
+ {
352
+ "completion_length": 314.625,
353
+ "epoch": 0.0004357886217666041,
354
+ "grad_norm": 3.5,
355
+ "kl": 0.0007861174817662686,
356
+ "learning_rate": 4.3577505706578135e-08,
357
+ "loss": 0.0,
358
+ "reward": 3.420614719390869,
359
+ "reward_std": 0.20994042605161667,
360
+ "rewards/combined_metrics_reward": 3.071489691734314,
361
+ "rewards/reasoning_quality_reward": 0.24650000780820847,
362
+ "rewards/soft_format_reward_func": 0.0,
363
+ "rewards/strict_format_reward_func": 0.0,
364
+ "rewards/xml_structure_reward": 0.0,
365
+ "rewards/xmlcount_reward_func": 0.10262499377131462,
366
+ "step": 21
367
+ },
368
+ {
369
+ "completion_length": 174.6875,
370
+ "epoch": 0.0004565404608983471,
371
+ "grad_norm": 5.53125,
372
+ "kl": 0.0008638710132800043,
373
+ "learning_rate": 4.5652625025938996e-08,
374
+ "loss": 0.0,
375
+ "reward": 3.415018081665039,
376
+ "reward_std": 0.3386603444814682,
377
+ "rewards/combined_metrics_reward": 2.8555182218551636,
378
+ "rewards/reasoning_quality_reward": 0.2459999993443489,
379
+ "rewards/soft_format_reward_func": 0.0,
380
+ "rewards/strict_format_reward_func": 0.0,
381
+ "rewards/xml_structure_reward": 0.0,
382
+ "rewards/xmlcount_reward_func": 0.31349998712539673,
383
+ "step": 22
384
+ },
385
+ {
386
+ "completion_length": 122.6875,
387
+ "epoch": 0.00047729230003009017,
388
+ "grad_norm": 5.28125,
389
+ "kl": 0.0008464560960419476,
390
+ "learning_rate": 4.7727744345299857e-08,
391
+ "loss": 0.0,
392
+ "reward": 3.47759747505188,
393
+ "reward_std": 0.247322216629982,
394
+ "rewards/combined_metrics_reward": 2.998347520828247,
395
+ "rewards/reasoning_quality_reward": 0.23250000178813934,
396
+ "rewards/soft_format_reward_func": 0.0,
397
+ "rewards/strict_format_reward_func": 0.0,
398
+ "rewards/xml_structure_reward": 0.0,
399
+ "rewards/xmlcount_reward_func": 0.24674999713897705,
400
+ "step": 23
401
+ },
402
+ {
403
+ "completion_length": 120.75,
404
+ "epoch": 0.0004980441391618332,
405
+ "grad_norm": 7.21875,
406
+ "kl": 0.0010764457983896136,
407
+ "learning_rate": 4.980286366466072e-08,
408
+ "loss": 0.0,
409
+ "reward": 4.416310787200928,
410
+ "reward_std": 0.26038799434900284,
411
+ "rewards/combined_metrics_reward": 3.790060877799988,
412
+ "rewards/reasoning_quality_reward": 0.2904999926686287,
413
+ "rewards/soft_format_reward_func": 0.0,
414
+ "rewards/strict_format_reward_func": 0.0,
415
+ "rewards/xml_structure_reward": 0.0,
416
+ "rewards/xmlcount_reward_func": 0.3357499986886978,
417
+ "step": 24
418
+ },
419
+ {
420
+ "completion_length": 114.3125,
421
+ "epoch": 0.0005187959782935763,
422
+ "grad_norm": 9.4375,
423
+ "kl": 0.0011009047157131135,
424
+ "learning_rate": 5.187798298402159e-08,
425
+ "loss": 0.0,
426
+ "reward": 4.216593503952026,
427
+ "reward_std": 0.2685175836086273,
428
+ "rewards/combined_metrics_reward": 3.7737183570861816,
429
+ "rewards/reasoning_quality_reward": 0.2369999960064888,
430
+ "rewards/soft_format_reward_func": 0.0,
431
+ "rewards/strict_format_reward_func": 0.0,
432
+ "rewards/xml_structure_reward": 0.0,
433
+ "rewards/xmlcount_reward_func": 0.2058749943971634,
434
+ "step": 25
435
+ },
436
+ {
437
+ "completion_length": 148.0625,
438
+ "epoch": 0.0005395478174253193,
439
+ "grad_norm": 5.0,
440
+ "kl": 0.0008934343059081584,
441
+ "learning_rate": 5.395310230338245e-08,
442
+ "loss": 0.0,
443
+ "reward": 2.4447922706604004,
444
+ "reward_std": 0.2603985369205475,
445
+ "rewards/combined_metrics_reward": 2.038667142391205,
446
+ "rewards/reasoning_quality_reward": 0.328000009059906,
447
+ "rewards/soft_format_reward_func": 0.0,
448
+ "rewards/strict_format_reward_func": 0.0,
449
+ "rewards/xml_structure_reward": 0.0,
450
+ "rewards/xmlcount_reward_func": 0.07812499720603228,
451
+ "step": 26
452
+ },
453
+ {
454
+ "completion_length": 148.875,
455
+ "epoch": 0.0005602996565570624,
456
+ "grad_norm": 6.09375,
457
+ "kl": 0.0008044805726967752,
458
+ "learning_rate": 5.602822162274331e-08,
459
+ "loss": 0.0,
460
+ "reward": 5.053812265396118,
461
+ "reward_std": 0.26566092669963837,
462
+ "rewards/combined_metrics_reward": 4.4378745555877686,
463
+ "rewards/reasoning_quality_reward": 0.28050000965595245,
464
+ "rewards/soft_format_reward_func": 0.0,
465
+ "rewards/strict_format_reward_func": 0.0,
466
+ "rewards/xml_structure_reward": 0.0,
467
+ "rewards/xmlcount_reward_func": 0.33543749898672104,
468
+ "step": 27
469
+ },
470
+ {
471
+ "completion_length": 112.1875,
472
+ "epoch": 0.0005810514956888054,
473
+ "grad_norm": 6.65625,
474
+ "kl": 0.0009265629341825843,
475
+ "learning_rate": 5.8103340942104173e-08,
476
+ "loss": 0.0,
477
+ "reward": 4.751622676849365,
478
+ "reward_std": 0.28057825565338135,
479
+ "rewards/combined_metrics_reward": 4.145372629165649,
480
+ "rewards/reasoning_quality_reward": 0.3009999990463257,
481
+ "rewards/soft_format_reward_func": 0.0,
482
+ "rewards/strict_format_reward_func": 0.0,
483
+ "rewards/xml_structure_reward": 0.0,
484
+ "rewards/xmlcount_reward_func": 0.30525000393390656,
485
+ "step": 28
486
+ },
487
+ {
488
+ "completion_length": 259.4375,
489
+ "epoch": 0.0006018033348205485,
490
+ "grad_norm": 4.8125,
491
+ "kl": 0.001204434665851295,
492
+ "learning_rate": 6.017846026146504e-08,
493
+ "loss": 0.0,
494
+ "reward": 2.505348324775696,
495
+ "reward_std": 0.3394507169723511,
496
+ "rewards/combined_metrics_reward": 1.9506609439849854,
497
+ "rewards/reasoning_quality_reward": 0.2919999957084656,
498
+ "rewards/soft_format_reward_func": 0.0,
499
+ "rewards/strict_format_reward_func": 0.0,
500
+ "rewards/xml_structure_reward": 0.0,
501
+ "rewards/xmlcount_reward_func": 0.2626874968409538,
502
+ "step": 29
503
+ },
504
+ {
505
+ "completion_length": 218.0625,
506
+ "epoch": 0.0006225551739522915,
507
+ "grad_norm": 4.15625,
508
+ "kl": 0.0007582100224681199,
509
+ "learning_rate": 6.22535795808259e-08,
510
+ "loss": 0.0,
511
+ "reward": 3.580325126647949,
512
+ "reward_std": 0.2678277790546417,
513
+ "rewards/combined_metrics_reward": 2.971512794494629,
514
+ "rewards/reasoning_quality_reward": 0.32750000059604645,
515
+ "rewards/soft_format_reward_func": 0.0,
516
+ "rewards/strict_format_reward_func": 0.0,
517
+ "rewards/xml_structure_reward": 0.0,
518
+ "rewards/xmlcount_reward_func": 0.281312495470047,
519
+ "step": 30
520
+ },
521
+ {
522
+ "completion_length": 160.4375,
523
+ "epoch": 0.0006433070130840346,
524
+ "grad_norm": 5.375,
525
+ "kl": 0.0009831477655097842,
526
+ "learning_rate": 6.432869890018676e-08,
527
+ "loss": 0.0,
528
+ "reward": 4.173954963684082,
529
+ "reward_std": 0.23199134320020676,
530
+ "rewards/combined_metrics_reward": 3.6628923416137695,
531
+ "rewards/reasoning_quality_reward": 0.24249999225139618,
532
+ "rewards/soft_format_reward_func": 0.0,
533
+ "rewards/strict_format_reward_func": 0.0,
534
+ "rewards/xml_structure_reward": 0.0,
535
+ "rewards/xmlcount_reward_func": 0.2685624957084656,
536
+ "step": 31
537
+ },
538
+ {
539
+ "completion_length": 168.375,
540
+ "epoch": 0.0006640588522157776,
541
+ "grad_norm": 5.03125,
542
+ "kl": 0.0008805320831015706,
543
+ "learning_rate": 6.640381821954764e-08,
544
+ "loss": 0.0,
545
+ "reward": 3.462260603904724,
546
+ "reward_std": 0.3302922993898392,
547
+ "rewards/combined_metrics_reward": 2.974635362625122,
548
+ "rewards/reasoning_quality_reward": 0.26900000125169754,
549
+ "rewards/soft_format_reward_func": 0.0,
550
+ "rewards/strict_format_reward_func": 0.0,
551
+ "rewards/xml_structure_reward": 0.0,
552
+ "rewards/xmlcount_reward_func": 0.2186249978840351,
553
+ "step": 32
554
+ },
555
+ {
556
+ "completion_length": 120.6875,
557
+ "epoch": 0.0006848106913475207,
558
+ "grad_norm": 5.4375,
559
+ "kl": 0.0011203565227333456,
560
+ "learning_rate": 6.84789375389085e-08,
561
+ "loss": 0.0,
562
+ "reward": 4.64396858215332,
563
+ "reward_std": 0.24607308208942413,
564
+ "rewards/combined_metrics_reward": 4.113155841827393,
565
+ "rewards/reasoning_quality_reward": 0.28450000286102295,
566
+ "rewards/soft_format_reward_func": 0.0,
567
+ "rewards/strict_format_reward_func": 0.0,
568
+ "rewards/xml_structure_reward": 0.0,
569
+ "rewards/xmlcount_reward_func": 0.2463124915957451,
570
+ "step": 33
571
+ },
572
+ {
573
+ "completion_length": 260.75,
574
+ "epoch": 0.0007055625304792637,
575
+ "grad_norm": 3.40625,
576
+ "kl": 0.0008566071046516299,
577
+ "learning_rate": 7.055405685826936e-08,
578
+ "loss": 0.0,
579
+ "reward": 2.483691453933716,
580
+ "reward_std": 0.3964230865240097,
581
+ "rewards/combined_metrics_reward": 1.978253960609436,
582
+ "rewards/reasoning_quality_reward": 0.2994999885559082,
583
+ "rewards/soft_format_reward_func": 0.0,
584
+ "rewards/strict_format_reward_func": 0.0,
585
+ "rewards/xml_structure_reward": 0.0,
586
+ "rewards/xmlcount_reward_func": 0.20593749731779099,
587
+ "step": 34
588
+ },
589
+ {
590
+ "completion_length": 210.9375,
591
+ "epoch": 0.0007263143696110068,
592
+ "grad_norm": 4.625,
593
+ "kl": 0.0009020040452014655,
594
+ "learning_rate": 7.262917617763022e-08,
595
+ "loss": 0.0,
596
+ "reward": 3.403906762599945,
597
+ "reward_std": 0.29350268095731735,
598
+ "rewards/combined_metrics_reward": 2.922406792640686,
599
+ "rewards/reasoning_quality_reward": 0.2539999932050705,
600
+ "rewards/soft_format_reward_func": 0.0,
601
+ "rewards/strict_format_reward_func": 0.0,
602
+ "rewards/xml_structure_reward": 0.0,
603
+ "rewards/xmlcount_reward_func": 0.22749999910593033,
604
+ "step": 35
605
+ },
606
+ {
607
+ "completion_length": 172.0625,
608
+ "epoch": 0.0007470662087427499,
609
+ "grad_norm": 5.09375,
610
+ "kl": 0.0009576545562595129,
611
+ "learning_rate": 7.470429549699109e-08,
612
+ "loss": 0.0,
613
+ "reward": 3.256548285484314,
614
+ "reward_std": 0.2521658092737198,
615
+ "rewards/combined_metrics_reward": 2.8002982139587402,
616
+ "rewards/reasoning_quality_reward": 0.28050000965595245,
617
+ "rewards/soft_format_reward_func": 0.0,
618
+ "rewards/strict_format_reward_func": 0.0,
619
+ "rewards/xml_structure_reward": 0.0,
620
+ "rewards/xmlcount_reward_func": 0.1757499985396862,
621
+ "step": 36
622
+ },
623
+ {
624
+ "completion_length": 166.25,
625
+ "epoch": 0.0007678180478744929,
626
+ "grad_norm": 5.71875,
627
+ "kl": 0.000980779790552333,
628
+ "learning_rate": 7.677941481635195e-08,
629
+ "loss": 0.0,
630
+ "reward": 3.1306052207946777,
631
+ "reward_std": 0.3043363615870476,
632
+ "rewards/combined_metrics_reward": 2.6529802083969116,
633
+ "rewards/reasoning_quality_reward": 0.2474999874830246,
634
+ "rewards/soft_format_reward_func": 0.0,
635
+ "rewards/strict_format_reward_func": 0.0,
636
+ "rewards/xml_structure_reward": 0.0,
637
+ "rewards/xmlcount_reward_func": 0.23012499511241913,
638
+ "step": 37
639
+ },
640
+ {
641
+ "completion_length": 237.25,
642
+ "epoch": 0.000788569887006236,
643
+ "grad_norm": 3.15625,
644
+ "kl": 0.0008010372694116086,
645
+ "learning_rate": 7.885453413571281e-08,
646
+ "loss": 0.0,
647
+ "reward": 3.2689459323883057,
648
+ "reward_std": 0.2945689186453819,
649
+ "rewards/combined_metrics_reward": 2.759570837020874,
650
+ "rewards/reasoning_quality_reward": 0.2710000053048134,
651
+ "rewards/soft_format_reward_func": 0.0,
652
+ "rewards/strict_format_reward_func": 0.0,
653
+ "rewards/xml_structure_reward": 0.0,
654
+ "rewards/xmlcount_reward_func": 0.2383749932050705,
655
+ "step": 38
656
+ },
657
+ {
658
+ "completion_length": 166.8125,
659
+ "epoch": 0.000809321726137979,
660
+ "grad_norm": 4.9375,
661
+ "kl": 0.0008458096708636731,
662
+ "learning_rate": 8.092965345507367e-08,
663
+ "loss": 0.0,
664
+ "reward": 2.4140647649765015,
665
+ "reward_std": 0.23616982996463776,
666
+ "rewards/combined_metrics_reward": 1.755127191543579,
667
+ "rewards/reasoning_quality_reward": 0.3149999976158142,
668
+ "rewards/soft_format_reward_func": 0.0,
669
+ "rewards/strict_format_reward_func": 0.0,
670
+ "rewards/xml_structure_reward": 0.0,
671
+ "rewards/xmlcount_reward_func": 0.3439375013113022,
672
+ "step": 39
673
+ },
674
+ {
675
+ "completion_length": 165.0625,
676
+ "epoch": 0.0008300735652697221,
677
+ "grad_norm": 4.90625,
678
+ "kl": 0.0009987938101403415,
679
+ "learning_rate": 8.300477277443454e-08,
680
+ "loss": 0.0,
681
+ "reward": 2.676035165786743,
682
+ "reward_std": 0.2658289149403572,
683
+ "rewards/combined_metrics_reward": 2.2266602516174316,
684
+ "rewards/reasoning_quality_reward": 0.2645000070333481,
685
+ "rewards/soft_format_reward_func": 0.0,
686
+ "rewards/strict_format_reward_func": 0.0,
687
+ "rewards/xml_structure_reward": 0.0,
688
+ "rewards/xmlcount_reward_func": 0.18487498909235,
689
+ "step": 40
690
+ },
691
+ {
692
+ "completion_length": 155.75,
693
+ "epoch": 0.000850825404401465,
694
+ "grad_norm": 5.875,
695
+ "kl": 0.0009093136177398264,
696
+ "learning_rate": 8.50798920937954e-08,
697
+ "loss": 0.0,
698
+ "reward": 3.9275256395339966,
699
+ "reward_std": 0.312641903758049,
700
+ "rewards/combined_metrics_reward": 3.3940881490707397,
701
+ "rewards/reasoning_quality_reward": 0.24450001120567322,
702
+ "rewards/soft_format_reward_func": 0.0,
703
+ "rewards/strict_format_reward_func": 0.0,
704
+ "rewards/xml_structure_reward": 0.0,
705
+ "rewards/xmlcount_reward_func": 0.2889374792575836,
706
+ "step": 41
707
+ },
708
+ {
709
+ "completion_length": 184.25,
710
+ "epoch": 0.0008715772435332081,
711
+ "grad_norm": 4.90625,
712
+ "kl": 0.0008097864920273423,
713
+ "learning_rate": 8.715501141315627e-08,
714
+ "loss": 0.0,
715
+ "reward": 3.840208649635315,
716
+ "reward_std": 0.28703561425209045,
717
+ "rewards/combined_metrics_reward": 3.4097087383270264,
718
+ "rewards/reasoning_quality_reward": 0.24950000643730164,
719
+ "rewards/soft_format_reward_func": 0.0,
720
+ "rewards/strict_format_reward_func": 0.0,
721
+ "rewards/xml_structure_reward": 0.0,
722
+ "rewards/xmlcount_reward_func": 0.1809999942779541,
723
+ "step": 42
724
+ },
725
+ {
726
+ "completion_length": 223.1875,
727
+ "epoch": 0.0008923290826649511,
728
+ "grad_norm": 3.875,
729
+ "kl": 0.0009467077325098217,
730
+ "learning_rate": 8.923013073251713e-08,
731
+ "loss": 0.0,
732
+ "reward": 3.9015913009643555,
733
+ "reward_std": 0.2828889638185501,
734
+ "rewards/combined_metrics_reward": 3.418341279029846,
735
+ "rewards/reasoning_quality_reward": 0.36550000309944153,
736
+ "rewards/soft_format_reward_func": 0.0,
737
+ "rewards/strict_format_reward_func": 0.0,
738
+ "rewards/xml_structure_reward": 0.0,
739
+ "rewards/xmlcount_reward_func": 0.11774998903274536,
740
+ "step": 43
741
+ },
742
+ {
743
+ "completion_length": 162.5625,
744
+ "epoch": 0.0009130809217966942,
745
+ "grad_norm": 4.71875,
746
+ "kl": 0.0010366241331212223,
747
+ "learning_rate": 9.130525005187799e-08,
748
+ "loss": 0.0,
749
+ "reward": 4.191276550292969,
750
+ "reward_std": 0.24220437556505203,
751
+ "rewards/combined_metrics_reward": 3.6448391675949097,
752
+ "rewards/reasoning_quality_reward": 0.37150000035762787,
753
+ "rewards/soft_format_reward_func": 0.0,
754
+ "rewards/strict_format_reward_func": 0.0,
755
+ "rewards/xml_structure_reward": 0.0,
756
+ "rewards/xmlcount_reward_func": 0.17493749782443047,
757
+ "step": 44
758
+ },
759
+ {
760
+ "completion_length": 213.0625,
761
+ "epoch": 0.0009338327609284372,
762
+ "grad_norm": 4.03125,
763
+ "kl": 0.0007707541808485985,
764
+ "learning_rate": 9.338036937123885e-08,
765
+ "loss": 0.0,
766
+ "reward": 3.1916075944900513,
767
+ "reward_std": 0.27592886984348297,
768
+ "rewards/combined_metrics_reward": 2.6236701011657715,
769
+ "rewards/reasoning_quality_reward": 0.310000017285347,
770
+ "rewards/soft_format_reward_func": 0.0,
771
+ "rewards/strict_format_reward_func": 0.0,
772
+ "rewards/xml_structure_reward": 0.0,
773
+ "rewards/xmlcount_reward_func": 0.2579375058412552,
774
+ "step": 45
775
+ },
776
+ {
777
+ "completion_length": 179.75,
778
+ "epoch": 0.0009545846000601803,
779
+ "grad_norm": 5.75,
780
+ "kl": 0.000993413559626788,
781
+ "learning_rate": 9.545548869059971e-08,
782
+ "loss": 0.0,
783
+ "reward": 3.664252519607544,
784
+ "reward_std": 0.20358892530202866,
785
+ "rewards/combined_metrics_reward": 3.1256275177001953,
786
+ "rewards/reasoning_quality_reward": 0.24950001388788223,
787
+ "rewards/soft_format_reward_func": 0.0,
788
+ "rewards/strict_format_reward_func": 0.0,
789
+ "rewards/xml_structure_reward": 0.0,
790
+ "rewards/xmlcount_reward_func": 0.2891249805688858,
791
+ "step": 46
792
+ },
793
+ {
794
+ "completion_length": 240.5625,
795
+ "epoch": 0.0009753364391919234,
796
+ "grad_norm": 3.875,
797
+ "kl": 0.000850174343213439,
798
+ "learning_rate": 9.753060800996057e-08,
799
+ "loss": 0.0,
800
+ "reward": 2.6008338928222656,
801
+ "reward_std": 0.30968883633613586,
802
+ "rewards/combined_metrics_reward": 2.1074588298797607,
803
+ "rewards/reasoning_quality_reward": 0.32499998807907104,
804
+ "rewards/soft_format_reward_func": 0.0,
805
+ "rewards/strict_format_reward_func": 0.0,
806
+ "rewards/xml_structure_reward": 0.0,
807
+ "rewards/xmlcount_reward_func": 0.16837500035762787,
808
+ "step": 47
809
+ },
810
+ {
811
+ "completion_length": 193.25,
812
+ "epoch": 0.0009960882783236664,
813
+ "grad_norm": 4.5,
814
+ "kl": 0.0009154146537184715,
815
+ "learning_rate": 9.960572732932143e-08,
816
+ "loss": 0.0,
817
+ "reward": 3.081048846244812,
818
+ "reward_std": 0.3781813085079193,
819
+ "rewards/combined_metrics_reward": 2.601736307144165,
820
+ "rewards/reasoning_quality_reward": 0.28349998593330383,
821
+ "rewards/soft_format_reward_func": 0.0,
822
+ "rewards/strict_format_reward_func": 0.0,
823
+ "rewards/xml_structure_reward": 0.0,
824
+ "rewards/xmlcount_reward_func": 0.19581250101327896,
825
+ "step": 48
826
+ },
827
+ {
828
+ "completion_length": 170.6875,
829
+ "epoch": 0.0010168401174554095,
830
+ "grad_norm": 4.75,
831
+ "kl": 0.0008789874846115708,
832
+ "learning_rate": 1.0168084664868232e-07,
833
+ "loss": 0.0,
834
+ "reward": 4.306732654571533,
835
+ "reward_std": 0.2756723612546921,
836
+ "rewards/combined_metrics_reward": 3.707295060157776,
837
+ "rewards/reasoning_quality_reward": 0.35350000858306885,
838
+ "rewards/soft_format_reward_func": 0.0,
839
+ "rewards/strict_format_reward_func": 0.0,
840
+ "rewards/xml_structure_reward": 0.0,
841
+ "rewards/xmlcount_reward_func": 0.24593748897314072,
842
+ "step": 49
843
+ },
844
+ {
845
+ "completion_length": 164.1875,
846
+ "epoch": 0.0010375919565871526,
847
+ "grad_norm": 5.59375,
848
+ "kl": 0.0008784849778749049,
849
+ "learning_rate": 1.0375596596804318e-07,
850
+ "loss": 0.0,
851
+ "reward": 3.275169014930725,
852
+ "reward_std": 0.2582494840025902,
853
+ "rewards/combined_metrics_reward": 2.8076691031455994,
854
+ "rewards/reasoning_quality_reward": 0.2840000092983246,
855
+ "rewards/soft_format_reward_func": 0.0,
856
+ "rewards/strict_format_reward_func": 0.0,
857
+ "rewards/xml_structure_reward": 0.0,
858
+ "rewards/xmlcount_reward_func": 0.18350000120699406,
859
+ "step": 50
860
+ },
861
+ {
862
+ "completion_length": 189.625,
863
+ "epoch": 0.0010583437957188955,
864
+ "grad_norm": 4.125,
865
+ "kl": 0.0008781255746725947,
866
+ "learning_rate": 1.0583108528740404e-07,
867
+ "loss": 0.0,
868
+ "reward": 2.882705569267273,
869
+ "reward_std": 0.22871624678373337,
870
+ "rewards/combined_metrics_reward": 2.2585803866386414,
871
+ "rewards/reasoning_quality_reward": 0.3425000011920929,
872
+ "rewards/soft_format_reward_func": 0.0,
873
+ "rewards/strict_format_reward_func": 0.0,
874
+ "rewards/xml_structure_reward": 0.0,
875
+ "rewards/xmlcount_reward_func": 0.28162500262260437,
876
+ "step": 51
877
+ },
878
+ {
879
+ "completion_length": 122.1875,
880
+ "epoch": 0.0010790956348506386,
881
+ "grad_norm": 5.15625,
882
+ "kl": 0.0007856120937503874,
883
+ "learning_rate": 1.079062046067649e-07,
884
+ "loss": 0.0,
885
+ "reward": 5.808703899383545,
886
+ "reward_std": 0.2522203177213669,
887
+ "rewards/combined_metrics_reward": 5.237016201019287,
888
+ "rewards/reasoning_quality_reward": 0.25200001895427704,
889
+ "rewards/soft_format_reward_func": 0.0,
890
+ "rewards/strict_format_reward_func": 0.0,
891
+ "rewards/xml_structure_reward": 0.0,
892
+ "rewards/xmlcount_reward_func": 0.31968750059604645,
893
+ "step": 52
894
+ },
895
+ {
896
+ "completion_length": 143.1875,
897
+ "epoch": 0.0010998474739823817,
898
+ "grad_norm": 4.90625,
899
+ "kl": 0.000852541095810011,
900
+ "learning_rate": 1.0998132392612576e-07,
901
+ "loss": 0.0,
902
+ "reward": 5.127512693405151,
903
+ "reward_std": 0.24172963201999664,
904
+ "rewards/combined_metrics_reward": 4.462950229644775,
905
+ "rewards/reasoning_quality_reward": 0.29649999737739563,
906
+ "rewards/soft_format_reward_func": 0.0,
907
+ "rewards/strict_format_reward_func": 0.0,
908
+ "rewards/xml_structure_reward": 0.0,
909
+ "rewards/xmlcount_reward_func": 0.36806248128414154,
910
+ "step": 53
911
+ },
912
+ {
913
+ "completion_length": 213.8125,
914
+ "epoch": 0.0011205993131141248,
915
+ "grad_norm": 4.40625,
916
+ "kl": 0.000927605084143579,
917
+ "learning_rate": 1.1205644324548663e-07,
918
+ "loss": 0.0,
919
+ "reward": 2.6862598657608032,
920
+ "reward_std": 0.30164453387260437,
921
+ "rewards/combined_metrics_reward": 2.109447479248047,
922
+ "rewards/reasoning_quality_reward": 0.3355000168085098,
923
+ "rewards/soft_format_reward_func": 0.0,
924
+ "rewards/strict_format_reward_func": 0.0,
925
+ "rewards/xml_structure_reward": 0.0,
926
+ "rewards/xmlcount_reward_func": 0.24131249636411667,
927
+ "step": 54
928
+ },
929
+ {
930
+ "completion_length": 118.4375,
931
+ "epoch": 0.0011413511522458677,
932
+ "grad_norm": 6.09375,
933
+ "kl": 0.0009260955848731101,
934
+ "learning_rate": 1.1413156256484749e-07,
935
+ "loss": 0.0,
936
+ "reward": 4.091360092163086,
937
+ "reward_std": 0.1810939759016037,
938
+ "rewards/combined_metrics_reward": 3.496672511100769,
939
+ "rewards/reasoning_quality_reward": 0.2590000182390213,
940
+ "rewards/soft_format_reward_func": 0.0,
941
+ "rewards/strict_format_reward_func": 0.0,
942
+ "rewards/xml_structure_reward": 0.0,
943
+ "rewards/xmlcount_reward_func": 0.3356874883174896,
944
+ "step": 55
945
+ },
946
+ {
947
+ "completion_length": 238.0625,
948
+ "epoch": 0.0011621029913776108,
949
+ "grad_norm": 5.59375,
950
+ "kl": 0.0009438655688427389,
951
+ "learning_rate": 1.1620668188420835e-07,
952
+ "loss": 0.0,
953
+ "reward": 2.564783811569214,
954
+ "reward_std": 0.25203585624694824,
955
+ "rewards/combined_metrics_reward": 2.0044714212417603,
956
+ "rewards/reasoning_quality_reward": 0.2760000079870224,
957
+ "rewards/soft_format_reward_func": 0.0,
958
+ "rewards/strict_format_reward_func": 0.0,
959
+ "rewards/xml_structure_reward": 0.0,
960
+ "rewards/xmlcount_reward_func": 0.28431248664855957,
961
+ "step": 56
962
+ },
963
+ {
964
+ "completion_length": 130.1875,
965
+ "epoch": 0.0011828548305093539,
966
+ "grad_norm": 5.84375,
967
+ "kl": 0.0010885814554058015,
968
+ "learning_rate": 1.1828180120356922e-07,
969
+ "loss": 0.0,
970
+ "reward": 2.6850783824920654,
971
+ "reward_std": 0.18680675327777863,
972
+ "rewards/combined_metrics_reward": 2.11601585149765,
973
+ "rewards/reasoning_quality_reward": 0.3240000009536743,
974
+ "rewards/soft_format_reward_func": 0.0,
975
+ "rewards/strict_format_reward_func": 0.0,
976
+ "rewards/xml_structure_reward": 0.0,
977
+ "rewards/xmlcount_reward_func": 0.24506250023841858,
978
+ "step": 57
979
+ },
980
+ {
981
+ "completion_length": 212.6875,
982
+ "epoch": 0.001203606669641097,
983
+ "grad_norm": 5.75,
984
+ "kl": 0.0010209570755250752,
985
+ "learning_rate": 1.2035692052293008e-07,
986
+ "loss": 0.0,
987
+ "reward": 2.956907629966736,
988
+ "reward_std": 0.26194363459944725,
989
+ "rewards/combined_metrics_reward": 2.3626577854156494,
990
+ "rewards/reasoning_quality_reward": 0.29999999701976776,
991
+ "rewards/soft_format_reward_func": 0.0,
992
+ "rewards/strict_format_reward_func": 0.0,
993
+ "rewards/xml_structure_reward": 0.0,
994
+ "rewards/xmlcount_reward_func": 0.29424998909235,
995
+ "step": 58
996
+ },
997
+ {
998
+ "completion_length": 162.1875,
999
+ "epoch": 0.00122435850877284,
1000
+ "grad_norm": 6.75,
1001
+ "kl": 0.0010345281334593892,
1002
+ "learning_rate": 1.2243203984229094e-07,
1003
+ "loss": 0.0,
1004
+ "reward": 4.6007208824157715,
1005
+ "reward_std": 0.26878365874290466,
1006
+ "rewards/combined_metrics_reward": 4.06778347492218,
1007
+ "rewards/reasoning_quality_reward": 0.30550001561641693,
1008
+ "rewards/soft_format_reward_func": 0.0,
1009
+ "rewards/strict_format_reward_func": 0.0,
1010
+ "rewards/xml_structure_reward": 0.0,
1011
+ "rewards/xmlcount_reward_func": 0.22743749618530273,
1012
+ "step": 59
1013
+ },
1014
+ {
1015
+ "completion_length": 177.875,
1016
+ "epoch": 0.001245110347904583,
1017
+ "grad_norm": 4.5625,
1018
+ "kl": 0.0009323270642198622,
1019
+ "learning_rate": 1.245071591616518e-07,
1020
+ "loss": 0.0,
1021
+ "reward": 4.253264546394348,
1022
+ "reward_std": 0.29857683181762695,
1023
+ "rewards/combined_metrics_reward": 3.7184518575668335,
1024
+ "rewards/reasoning_quality_reward": 0.3349999934434891,
1025
+ "rewards/soft_format_reward_func": 0.0,
1026
+ "rewards/strict_format_reward_func": 0.0,
1027
+ "rewards/xml_structure_reward": 0.0,
1028
+ "rewards/xmlcount_reward_func": 0.19981250166893005,
1029
+ "step": 60
1030
+ },
1031
+ {
1032
+ "completion_length": 150.875,
1033
+ "epoch": 0.001265862187036326,
1034
+ "grad_norm": 4.71875,
1035
+ "kl": 0.0009517802391201258,
1036
+ "learning_rate": 1.2658227848101266e-07,
1037
+ "loss": 0.0,
1038
+ "reward": 2.9035253524780273,
1039
+ "reward_std": 0.21968870609998703,
1040
+ "rewards/combined_metrics_reward": 2.334587812423706,
1041
+ "rewards/reasoning_quality_reward": 0.3205000013113022,
1042
+ "rewards/soft_format_reward_func": 0.0,
1043
+ "rewards/strict_format_reward_func": 0.0,
1044
+ "rewards/xml_structure_reward": 0.0,
1045
+ "rewards/xmlcount_reward_func": 0.24843747913837433,
1046
+ "step": 61
1047
+ },
1048
+ {
1049
+ "completion_length": 175.4375,
1050
+ "epoch": 0.0012866140261680692,
1051
+ "grad_norm": 4.84375,
1052
+ "kl": 0.001134191348683089,
1053
+ "learning_rate": 1.2865739780037352e-07,
1054
+ "loss": 0.0,
1055
+ "reward": 3.045235753059387,
1056
+ "reward_std": 0.2987499535083771,
1057
+ "rewards/combined_metrics_reward": 2.544173240661621,
1058
+ "rewards/reasoning_quality_reward": 0.2459999993443489,
1059
+ "rewards/soft_format_reward_func": 0.0,
1060
+ "rewards/strict_format_reward_func": 0.0,
1061
+ "rewards/xml_structure_reward": 0.0,
1062
+ "rewards/xmlcount_reward_func": 0.2550624907016754,
1063
+ "step": 62
1064
+ },
1065
+ {
1066
+ "completion_length": 176.75,
1067
+ "epoch": 0.0013073658652998123,
1068
+ "grad_norm": 4.71875,
1069
+ "kl": 0.0009000462887343019,
1070
+ "learning_rate": 1.3073251711973439e-07,
1071
+ "loss": -0.0,
1072
+ "reward": 4.446258068084717,
1073
+ "reward_std": 0.13639461621642113,
1074
+ "rewards/combined_metrics_reward": 3.8028831481933594,
1075
+ "rewards/reasoning_quality_reward": 0.281500019133091,
1076
+ "rewards/soft_format_reward_func": 0.0,
1077
+ "rewards/strict_format_reward_func": 0.0,
1078
+ "rewards/xml_structure_reward": 0.0,
1079
+ "rewards/xmlcount_reward_func": 0.3618749901652336,
1080
+ "step": 63
1081
+ },
1082
+ {
1083
+ "completion_length": 146.75,
1084
+ "epoch": 0.0013281177044315552,
1085
+ "grad_norm": 4.5,
1086
+ "kl": 0.0008634670521132648,
1087
+ "learning_rate": 1.3280763643909527e-07,
1088
+ "loss": -0.0,
1089
+ "reward": 4.130820035934448,
1090
+ "reward_std": 0.2278589829802513,
1091
+ "rewards/combined_metrics_reward": 3.6308199167251587,
1092
+ "rewards/reasoning_quality_reward": 0.304999977350235,
1093
+ "rewards/soft_format_reward_func": 0.0,
1094
+ "rewards/strict_format_reward_func": 0.0,
1095
+ "rewards/xml_structure_reward": 0.0,
1096
+ "rewards/xmlcount_reward_func": 0.19500000029802322,
1097
+ "step": 64
1098
+ },
1099
+ {
1100
+ "completion_length": 151.875,
1101
+ "epoch": 0.0013488695435632983,
1102
+ "grad_norm": 6.5,
1103
+ "kl": 0.0010424230131320655,
1104
+ "learning_rate": 1.3488275575845613e-07,
1105
+ "loss": 0.0,
1106
+ "reward": 4.1674580574035645,
1107
+ "reward_std": 0.28048408031463623,
1108
+ "rewards/combined_metrics_reward": 3.575083017349243,
1109
+ "rewards/reasoning_quality_reward": 0.318000003695488,
1110
+ "rewards/soft_format_reward_func": 0.0,
1111
+ "rewards/strict_format_reward_func": 0.0,
1112
+ "rewards/xml_structure_reward": 0.0,
1113
+ "rewards/xmlcount_reward_func": 0.27437499165534973,
1114
+ "step": 65
1115
+ },
1116
+ {
1117
+ "completion_length": 174.75,
1118
+ "epoch": 0.0013696213826950414,
1119
+ "grad_norm": 5.3125,
1120
+ "kl": 0.0009348655585199594,
1121
+ "learning_rate": 1.36957875077817e-07,
1122
+ "loss": 0.0,
1123
+ "reward": 3.472010016441345,
1124
+ "reward_std": 0.2244405597448349,
1125
+ "rewards/combined_metrics_reward": 3.004634976387024,
1126
+ "rewards/reasoning_quality_reward": 0.28450000286102295,
1127
+ "rewards/soft_format_reward_func": 0.0,
1128
+ "rewards/strict_format_reward_func": 0.0,
1129
+ "rewards/xml_structure_reward": 0.0,
1130
+ "rewards/xmlcount_reward_func": 0.18287500366568565,
1131
+ "step": 66
1132
+ },
1133
+ {
1134
+ "completion_length": 135.0625,
1135
+ "epoch": 0.0013903732218267845,
1136
+ "grad_norm": 6.0625,
1137
+ "kl": 0.0010373267577961087,
1138
+ "learning_rate": 1.3903299439717785e-07,
1139
+ "loss": 0.0,
1140
+ "reward": 3.530911684036255,
1141
+ "reward_std": 0.29957813024520874,
1142
+ "rewards/combined_metrics_reward": 3.132599115371704,
1143
+ "rewards/reasoning_quality_reward": 0.2565000057220459,
1144
+ "rewards/soft_format_reward_func": 0.0,
1145
+ "rewards/strict_format_reward_func": 0.0,
1146
+ "rewards/xml_structure_reward": 0.0,
1147
+ "rewards/xmlcount_reward_func": 0.1418124921619892,
1148
+ "step": 67
1149
+ },
1150
+ {
1151
+ "completion_length": 216.4375,
1152
+ "epoch": 0.0014111250609585273,
1153
+ "grad_norm": 4.28125,
1154
+ "kl": 0.0007825276115909219,
1155
+ "learning_rate": 1.4110811371653872e-07,
1156
+ "loss": 0.0,
1157
+ "reward": 3.4641153812408447,
1158
+ "reward_std": 0.2696981579065323,
1159
+ "rewards/combined_metrics_reward": 2.9205528497695923,
1160
+ "rewards/reasoning_quality_reward": 0.27549999952316284,
1161
+ "rewards/soft_format_reward_func": 0.0,
1162
+ "rewards/strict_format_reward_func": 0.0,
1163
+ "rewards/xml_structure_reward": 0.0,
1164
+ "rewards/xmlcount_reward_func": 0.2680625021457672,
1165
+ "step": 68
1166
+ },
1167
+ {
1168
+ "completion_length": 184.625,
1169
+ "epoch": 0.0014318769000902704,
1170
+ "grad_norm": 5.71875,
1171
+ "kl": 0.0012683356180787086,
1172
+ "learning_rate": 1.4318323303589958e-07,
1173
+ "loss": 0.0,
1174
+ "reward": 5.19528603553772,
1175
+ "reward_std": 0.28438882529735565,
1176
+ "rewards/combined_metrics_reward": 4.754223346710205,
1177
+ "rewards/reasoning_quality_reward": 0.2554999887943268,
1178
+ "rewards/soft_format_reward_func": 0.0,
1179
+ "rewards/strict_format_reward_func": 0.0,
1180
+ "rewards/xml_structure_reward": 0.0,
1181
+ "rewards/xmlcount_reward_func": 0.18556250259280205,
1182
+ "step": 69
1183
+ },
1184
+ {
1185
+ "completion_length": 200.6875,
1186
+ "epoch": 0.0014526287392220135,
1187
+ "grad_norm": 4.25,
1188
+ "kl": 0.0008905293070711195,
1189
+ "learning_rate": 1.4525835235526044e-07,
1190
+ "loss": 0.0,
1191
+ "reward": 3.0607593059539795,
1192
+ "reward_std": 0.26176200062036514,
1193
+ "rewards/combined_metrics_reward": 2.555821657180786,
1194
+ "rewards/reasoning_quality_reward": 0.3034999966621399,
1195
+ "rewards/soft_format_reward_func": 0.0,
1196
+ "rewards/strict_format_reward_func": 0.0,
1197
+ "rewards/xml_structure_reward": 0.0,
1198
+ "rewards/xmlcount_reward_func": 0.20143749564886093,
1199
+ "step": 70
1200
+ },
1201
+ {
1202
+ "completion_length": 165.6875,
1203
+ "epoch": 0.0014733805783537566,
1204
+ "grad_norm": 5.3125,
1205
+ "kl": 0.0008913811179809272,
1206
+ "learning_rate": 1.473334716746213e-07,
1207
+ "loss": 0.0,
1208
+ "reward": 3.5411019325256348,
1209
+ "reward_std": 0.37085966765880585,
1210
+ "rewards/combined_metrics_reward": 3.118414282798767,
1211
+ "rewards/reasoning_quality_reward": 0.28199999034404755,
1212
+ "rewards/soft_format_reward_func": 0.0,
1213
+ "rewards/strict_format_reward_func": 0.0,
1214
+ "rewards/xml_structure_reward": 0.0,
1215
+ "rewards/xmlcount_reward_func": 0.140687495470047,
1216
+ "step": 71
1217
+ },
1218
+ {
1219
+ "completion_length": 171.125,
1220
+ "epoch": 0.0014941324174854997,
1221
+ "grad_norm": 4.375,
1222
+ "kl": 0.0009440038993488997,
1223
+ "learning_rate": 1.4940859099398218e-07,
1224
+ "loss": 0.0,
1225
+ "reward": 6.08599328994751,
1226
+ "reward_std": 0.405931681394577,
1227
+ "rewards/combined_metrics_reward": 5.6093058586120605,
1228
+ "rewards/reasoning_quality_reward": 0.31850001215934753,
1229
+ "rewards/soft_format_reward_func": 0.0,
1230
+ "rewards/strict_format_reward_func": 0.0,
1231
+ "rewards/xml_structure_reward": 0.0,
1232
+ "rewards/xmlcount_reward_func": 0.1581874843686819,
1233
+ "step": 72
1234
+ },
1235
+ {
1236
+ "completion_length": 189.6875,
1237
+ "epoch": 0.0015148842566172426,
1238
+ "grad_norm": 4.1875,
1239
+ "kl": 0.0010994974290952086,
1240
+ "learning_rate": 1.5148371031334305e-07,
1241
+ "loss": 0.0,
1242
+ "reward": 2.5608932971954346,
1243
+ "reward_std": 0.263590507209301,
1244
+ "rewards/combined_metrics_reward": 2.1282058358192444,
1245
+ "rewards/reasoning_quality_reward": 0.22100000083446503,
1246
+ "rewards/soft_format_reward_func": 0.0,
1247
+ "rewards/strict_format_reward_func": 0.0,
1248
+ "rewards/xml_structure_reward": 0.0,
1249
+ "rewards/xmlcount_reward_func": 0.21168749779462814,
1250
+ "step": 73
1251
+ },
1252
+ {
1253
+ "completion_length": 218.8125,
1254
+ "epoch": 0.0015356360957489857,
1255
+ "grad_norm": 3.75,
1256
+ "kl": 0.000962897262070328,
1257
+ "learning_rate": 1.535588296327039e-07,
1258
+ "loss": 0.0,
1259
+ "reward": 2.6438591480255127,
1260
+ "reward_std": 0.2856897562742233,
1261
+ "rewards/combined_metrics_reward": 2.2106717228889465,
1262
+ "rewards/reasoning_quality_reward": 0.23799999803304672,
1263
+ "rewards/soft_format_reward_func": 0.0,
1264
+ "rewards/strict_format_reward_func": 0.0,
1265
+ "rewards/xml_structure_reward": 0.0,
1266
+ "rewards/xmlcount_reward_func": 0.1951874941587448,
1267
+ "step": 74
1268
+ },
1269
+ {
1270
+ "completion_length": 205.9375,
1271
+ "epoch": 0.0015563879348807288,
1272
+ "grad_norm": 3.453125,
1273
+ "kl": 0.0007736819388810545,
1274
+ "learning_rate": 1.5563394895206477e-07,
1275
+ "loss": 0.0,
1276
+ "reward": 3.267431378364563,
1277
+ "reward_std": 0.12656611949205399,
1278
+ "rewards/combined_metrics_reward": 2.6237438917160034,
1279
+ "rewards/reasoning_quality_reward": 0.3205000013113022,
1280
+ "rewards/soft_format_reward_func": 0.0,
1281
+ "rewards/strict_format_reward_func": 0.0,
1282
+ "rewards/xml_structure_reward": 0.0,
1283
+ "rewards/xmlcount_reward_func": 0.3231875002384186,
1284
+ "step": 75
1285
+ },
1286
+ {
1287
+ "completion_length": 160.6875,
1288
+ "epoch": 0.001577139774012472,
1289
+ "grad_norm": 5.6875,
1290
+ "kl": 0.000964676437433809,
1291
+ "learning_rate": 1.5770906827142563e-07,
1292
+ "loss": 0.0,
1293
+ "reward": 2.7046583890914917,
1294
+ "reward_std": 0.3649689257144928,
1295
+ "rewards/combined_metrics_reward": 2.190345883369446,
1296
+ "rewards/reasoning_quality_reward": 0.25999999791383743,
1297
+ "rewards/soft_format_reward_func": 0.0,
1298
+ "rewards/strict_format_reward_func": 0.0,
1299
+ "rewards/xml_structure_reward": 0.0,
1300
+ "rewards/xmlcount_reward_func": 0.25431249290704727,
1301
+ "step": 76
1302
+ },
1303
+ {
1304
+ "completion_length": 176.625,
1305
+ "epoch": 0.0015978916131442148,
1306
+ "grad_norm": 4.96875,
1307
+ "kl": 0.0008983553561847657,
1308
+ "learning_rate": 1.597841875907865e-07,
1309
+ "loss": 0.0,
1310
+ "reward": 3.499585509300232,
1311
+ "reward_std": 0.2732354775071144,
1312
+ "rewards/combined_metrics_reward": 2.9143354892730713,
1313
+ "rewards/reasoning_quality_reward": 0.2985000014305115,
1314
+ "rewards/soft_format_reward_func": 0.0,
1315
+ "rewards/strict_format_reward_func": 0.0,
1316
+ "rewards/xml_structure_reward": 0.0,
1317
+ "rewards/xmlcount_reward_func": 0.2867499887943268,
1318
+ "step": 77
1319
+ },
1320
+ {
1321
+ "completion_length": 137.1875,
1322
+ "epoch": 0.001618643452275958,
1323
+ "grad_norm": 5.375,
1324
+ "kl": 0.0009333908674307168,
1325
+ "learning_rate": 1.6185930691014735e-07,
1326
+ "loss": 0.0,
1327
+ "reward": 3.707850217819214,
1328
+ "reward_std": 0.310992568731308,
1329
+ "rewards/combined_metrics_reward": 3.114287853240967,
1330
+ "rewards/reasoning_quality_reward": 0.2864999994635582,
1331
+ "rewards/soft_format_reward_func": 0.0,
1332
+ "rewards/strict_format_reward_func": 0.0,
1333
+ "rewards/xml_structure_reward": 0.0,
1334
+ "rewards/xmlcount_reward_func": 0.307062491774559,
1335
+ "step": 78
1336
+ },
1337
+ {
1338
+ "completion_length": 167.4375,
1339
+ "epoch": 0.001639395291407701,
1340
+ "grad_norm": 5.9375,
1341
+ "kl": 0.0010912244324572384,
1342
+ "learning_rate": 1.639344262295082e-07,
1343
+ "loss": 0.0,
1344
+ "reward": 3.3622095584869385,
1345
+ "reward_std": 0.22620216012001038,
1346
+ "rewards/combined_metrics_reward": 2.846834421157837,
1347
+ "rewards/reasoning_quality_reward": 0.27299999445676804,
1348
+ "rewards/soft_format_reward_func": 0.0,
1349
+ "rewards/strict_format_reward_func": 0.0,
1350
+ "rewards/xml_structure_reward": 0.0,
1351
+ "rewards/xmlcount_reward_func": 0.24237500131130219,
1352
+ "step": 79
1353
+ },
1354
+ {
1355
+ "completion_length": 187.0,
1356
+ "epoch": 0.0016601471305394441,
1357
+ "grad_norm": 4.34375,
1358
+ "kl": 0.0009224387467838824,
1359
+ "learning_rate": 1.6600954554886907e-07,
1360
+ "loss": 0.0,
1361
+ "reward": 3.860158324241638,
1362
+ "reward_std": 0.32335832715034485,
1363
+ "rewards/combined_metrics_reward": 3.2584707736968994,
1364
+ "rewards/reasoning_quality_reward": 0.35899999737739563,
1365
+ "rewards/soft_format_reward_func": 0.0,
1366
+ "rewards/strict_format_reward_func": 0.0,
1367
+ "rewards/xml_structure_reward": 0.0,
1368
+ "rewards/xmlcount_reward_func": 0.24268749356269836,
1369
+ "step": 80
1370
+ },
1371
+ {
1372
+ "completion_length": 128.3125,
1373
+ "epoch": 0.0016808989696711872,
1374
+ "grad_norm": 5.75,
1375
+ "kl": 0.0010056023602373898,
1376
+ "learning_rate": 1.6808466486822993e-07,
1377
+ "loss": 0.0,
1378
+ "reward": 3.8627277612686157,
1379
+ "reward_std": 0.17685160785913467,
1380
+ "rewards/combined_metrics_reward": 3.2791026830673218,
1381
+ "rewards/reasoning_quality_reward": 0.3135000169277191,
1382
+ "rewards/soft_format_reward_func": 0.0,
1383
+ "rewards/strict_format_reward_func": 0.0,
1384
+ "rewards/xml_structure_reward": 0.0,
1385
+ "rewards/xmlcount_reward_func": 0.27012498676776886,
1386
+ "step": 81
1387
+ },
1388
+ {
1389
+ "completion_length": 130.0625,
1390
+ "epoch": 0.00170165080880293,
1391
+ "grad_norm": 5.4375,
1392
+ "kl": 0.0009542278130538762,
1393
+ "learning_rate": 1.701597841875908e-07,
1394
+ "loss": 0.0,
1395
+ "reward": 4.066289901733398,
1396
+ "reward_std": 0.2911643013358116,
1397
+ "rewards/combined_metrics_reward": 3.557727575302124,
1398
+ "rewards/reasoning_quality_reward": 0.28450000286102295,
1399
+ "rewards/soft_format_reward_func": 0.0,
1400
+ "rewards/strict_format_reward_func": 0.0,
1401
+ "rewards/xml_structure_reward": 0.0,
1402
+ "rewards/xmlcount_reward_func": 0.2240625023841858,
1403
+ "step": 82
1404
+ },
1405
+ {
1406
+ "completion_length": 163.3125,
1407
+ "epoch": 0.0017224026479346732,
1408
+ "grad_norm": 5.21875,
1409
+ "kl": 0.0009847281617112458,
1410
+ "learning_rate": 1.7223490350695165e-07,
1411
+ "loss": 0.0,
1412
+ "reward": 3.124675989151001,
1413
+ "reward_std": 0.32101400196552277,
1414
+ "rewards/combined_metrics_reward": 2.7311758995056152,
1415
+ "rewards/reasoning_quality_reward": 0.20549999177455902,
1416
+ "rewards/soft_format_reward_func": 0.0,
1417
+ "rewards/strict_format_reward_func": 0.0,
1418
+ "rewards/xml_structure_reward": 0.0,
1419
+ "rewards/xmlcount_reward_func": 0.18799998611211777,
1420
+ "step": 83
1421
+ },
1422
+ {
1423
+ "completion_length": 153.625,
1424
+ "epoch": 0.0017431544870664163,
1425
+ "grad_norm": 5.625,
1426
+ "kl": 0.0009567763772793114,
1427
+ "learning_rate": 1.7431002282631254e-07,
1428
+ "loss": 0.0,
1429
+ "reward": 3.527772307395935,
1430
+ "reward_std": 0.2691190391778946,
1431
+ "rewards/combined_metrics_reward": 3.014397382736206,
1432
+ "rewards/reasoning_quality_reward": 0.2775000184774399,
1433
+ "rewards/soft_format_reward_func": 0.0,
1434
+ "rewards/strict_format_reward_func": 0.0,
1435
+ "rewards/xml_structure_reward": 0.0,
1436
+ "rewards/xmlcount_reward_func": 0.2358749955892563,
1437
+ "step": 84
1438
+ },
1439
+ {
1440
+ "completion_length": 164.6875,
1441
+ "epoch": 0.0017639063261981594,
1442
+ "grad_norm": 4.8125,
1443
+ "kl": 0.0008748667314648628,
1444
+ "learning_rate": 1.7638514214567337e-07,
1445
+ "loss": 0.0,
1446
+ "reward": 3.0405466556549072,
1447
+ "reward_std": 0.27828526496887207,
1448
+ "rewards/combined_metrics_reward": 2.4153592586517334,
1449
+ "rewards/reasoning_quality_reward": 0.3435000032186508,
1450
+ "rewards/soft_format_reward_func": 0.0,
1451
+ "rewards/strict_format_reward_func": 0.0,
1452
+ "rewards/xml_structure_reward": 0.0,
1453
+ "rewards/xmlcount_reward_func": 0.2816874831914902,
1454
+ "step": 85
1455
+ },
1456
+ {
1457
+ "completion_length": 295.875,
1458
+ "epoch": 0.0017846581653299023,
1459
+ "grad_norm": 3.4375,
1460
+ "kl": 0.0008926248410716653,
1461
+ "learning_rate": 1.7846026146503426e-07,
1462
+ "loss": 0.0,
1463
+ "reward": 2.6037517786026,
1464
+ "reward_std": 0.3151714950799942,
1465
+ "rewards/combined_metrics_reward": 2.1590644121170044,
1466
+ "rewards/reasoning_quality_reward": 0.34049999713897705,
1467
+ "rewards/soft_format_reward_func": 0.0,
1468
+ "rewards/strict_format_reward_func": 0.0,
1469
+ "rewards/xml_structure_reward": 0.0,
1470
+ "rewards/xmlcount_reward_func": 0.10418749414384365,
1471
+ "step": 86
1472
+ },
1473
+ {
1474
+ "completion_length": 162.5625,
1475
+ "epoch": 0.0018054100044616454,
1476
+ "grad_norm": 5.28125,
1477
+ "kl": 0.0008840092923492193,
1478
+ "learning_rate": 1.805353807843951e-07,
1479
+ "loss": 0.0,
1480
+ "reward": 2.5285197496414185,
1481
+ "reward_std": 0.23011047393083572,
1482
+ "rewards/combined_metrics_reward": 1.9362072944641113,
1483
+ "rewards/reasoning_quality_reward": 0.3240000158548355,
1484
+ "rewards/soft_format_reward_func": 0.0,
1485
+ "rewards/strict_format_reward_func": 0.0,
1486
+ "rewards/xml_structure_reward": 0.0,
1487
+ "rewards/xmlcount_reward_func": 0.2683124989271164,
1488
+ "step": 87
1489
+ },
1490
+ {
1491
+ "completion_length": 154.3125,
1492
+ "epoch": 0.0018261618435933885,
1493
+ "grad_norm": 5.46875,
1494
+ "kl": 0.0010054611775558442,
1495
+ "learning_rate": 1.8261050010375598e-07,
1496
+ "loss": 0.0,
1497
+ "reward": 4.551170349121094,
1498
+ "reward_std": 0.30171534419059753,
1499
+ "rewards/combined_metrics_reward": 3.8825457096099854,
1500
+ "rewards/reasoning_quality_reward": 0.3200000077486038,
1501
+ "rewards/soft_format_reward_func": 0.0,
1502
+ "rewards/strict_format_reward_func": 0.0,
1503
+ "rewards/xml_structure_reward": 0.0,
1504
+ "rewards/xmlcount_reward_func": 0.34862498939037323,
1505
+ "step": 88
1506
+ },
1507
+ {
1508
+ "completion_length": 203.125,
1509
+ "epoch": 0.0018469136827251316,
1510
+ "grad_norm": 3.9375,
1511
+ "kl": 0.0008199338044505566,
1512
+ "learning_rate": 1.8468561942311682e-07,
1513
+ "loss": 0.0,
1514
+ "reward": 4.652055978775024,
1515
+ "reward_std": 0.2673797756433487,
1516
+ "rewards/combined_metrics_reward": 4.009680986404419,
1517
+ "rewards/reasoning_quality_reward": 0.3164999932050705,
1518
+ "rewards/soft_format_reward_func": 0.0,
1519
+ "rewards/strict_format_reward_func": 0.0,
1520
+ "rewards/xml_structure_reward": 0.0,
1521
+ "rewards/xmlcount_reward_func": 0.325874999165535,
1522
+ "step": 89
1523
+ },
1524
+ {
1525
+ "completion_length": 171.0,
1526
+ "epoch": 0.0018676655218568745,
1527
+ "grad_norm": 4.9375,
1528
+ "kl": 0.0010065918322652578,
1529
+ "learning_rate": 1.867607387424777e-07,
1530
+ "loss": 0.0,
1531
+ "reward": 3.1197704076766968,
1532
+ "reward_std": 0.1659688800573349,
1533
+ "rewards/combined_metrics_reward": 2.631457805633545,
1534
+ "rewards/reasoning_quality_reward": 0.2929999977350235,
1535
+ "rewards/soft_format_reward_func": 0.0,
1536
+ "rewards/strict_format_reward_func": 0.0,
1537
+ "rewards/xml_structure_reward": 0.0,
1538
+ "rewards/xmlcount_reward_func": 0.1953124925494194,
1539
+ "step": 90
1540
+ },
1541
+ {
1542
+ "completion_length": 140.5625,
1543
+ "epoch": 0.0018884173609886176,
1544
+ "grad_norm": 5.21875,
1545
+ "kl": 0.000760748895118013,
1546
+ "learning_rate": 1.888358580618386e-07,
1547
+ "loss": 0.0,
1548
+ "reward": 5.6644792556762695,
1549
+ "reward_std": 0.34736819565296173,
1550
+ "rewards/combined_metrics_reward": 5.149729251861572,
1551
+ "rewards/reasoning_quality_reward": 0.2730000168085098,
1552
+ "rewards/soft_format_reward_func": 0.0,
1553
+ "rewards/strict_format_reward_func": 0.0,
1554
+ "rewards/xml_structure_reward": 0.0,
1555
+ "rewards/xmlcount_reward_func": 0.24174998700618744,
1556
+ "step": 91
1557
+ },
1558
+ {
1559
+ "completion_length": 178.5,
1560
+ "epoch": 0.0019091692001203607,
1561
+ "grad_norm": 4.71875,
1562
+ "kl": 0.0009657949267420918,
1563
+ "learning_rate": 1.9091097738119943e-07,
1564
+ "loss": 0.0,
1565
+ "reward": 3.2187812328338623,
1566
+ "reward_std": 0.2671329751610756,
1567
+ "rewards/combined_metrics_reward": 2.680343747138977,
1568
+ "rewards/reasoning_quality_reward": 0.28950001299381256,
1569
+ "rewards/soft_format_reward_func": 0.0,
1570
+ "rewards/strict_format_reward_func": 0.0,
1571
+ "rewards/xml_structure_reward": 0.0,
1572
+ "rewards/xmlcount_reward_func": 0.2489374727010727,
1573
+ "step": 92
1574
+ },
1575
+ {
1576
+ "completion_length": 135.4375,
1577
+ "epoch": 0.0019299210392521038,
1578
+ "grad_norm": 5.59375,
1579
+ "kl": 0.000826941104605794,
1580
+ "learning_rate": 1.9298609670056031e-07,
1581
+ "loss": -0.0,
1582
+ "reward": 3.6887762546539307,
1583
+ "reward_std": 0.228777214884758,
1584
+ "rewards/combined_metrics_reward": 3.226401448249817,
1585
+ "rewards/reasoning_quality_reward": 0.22950000315904617,
1586
+ "rewards/soft_format_reward_func": 0.0,
1587
+ "rewards/strict_format_reward_func": 0.0,
1588
+ "rewards/xml_structure_reward": 0.0,
1589
+ "rewards/xmlcount_reward_func": 0.23287498205900192,
1590
+ "step": 93
1591
+ },
1592
+ {
1593
+ "completion_length": 144.875,
1594
+ "epoch": 0.0019506728783838469,
1595
+ "grad_norm": 4.78125,
1596
+ "kl": 0.0010664030851330608,
1597
+ "learning_rate": 1.9506121601992115e-07,
1598
+ "loss": 0.0,
1599
+ "reward": 4.109573125839233,
1600
+ "reward_std": 0.19565286487340927,
1601
+ "rewards/combined_metrics_reward": 3.57882297039032,
1602
+ "rewards/reasoning_quality_reward": 0.3255000114440918,
1603
+ "rewards/soft_format_reward_func": 0.0,
1604
+ "rewards/strict_format_reward_func": 0.0,
1605
+ "rewards/xml_structure_reward": 0.0,
1606
+ "rewards/xmlcount_reward_func": 0.20524999499320984,
1607
+ "step": 94
1608
+ },
1609
+ {
1610
+ "completion_length": 149.875,
1611
+ "epoch": 0.0019714247175155897,
1612
+ "grad_norm": 4.25,
1613
+ "kl": 0.0007075394387356937,
1614
+ "learning_rate": 1.9713633533928203e-07,
1615
+ "loss": 0.0,
1616
+ "reward": 5.194463849067688,
1617
+ "reward_std": 0.30544108152389526,
1618
+ "rewards/combined_metrics_reward": 4.546401500701904,
1619
+ "rewards/reasoning_quality_reward": 0.3214999884366989,
1620
+ "rewards/soft_format_reward_func": 0.0,
1621
+ "rewards/strict_format_reward_func": 0.0,
1622
+ "rewards/xml_structure_reward": 0.0,
1623
+ "rewards/xmlcount_reward_func": 0.32656247913837433,
1624
+ "step": 95
1625
+ },
1626
+ {
1627
+ "completion_length": 163.0625,
1628
+ "epoch": 0.001992176556647333,
1629
+ "grad_norm": 5.0625,
1630
+ "kl": 0.0010073292651213706,
1631
+ "learning_rate": 1.9921145465864287e-07,
1632
+ "loss": 0.0,
1633
+ "reward": 4.315690040588379,
1634
+ "reward_std": 0.24308742582798004,
1635
+ "rewards/combined_metrics_reward": 3.774440050125122,
1636
+ "rewards/reasoning_quality_reward": 0.32349999248981476,
1637
+ "rewards/soft_format_reward_func": 0.0,
1638
+ "rewards/strict_format_reward_func": 0.0,
1639
+ "rewards/xml_structure_reward": 0.0,
1640
+ "rewards/xmlcount_reward_func": 0.21774998307228088,
1641
+ "step": 96
1642
+ },
1643
+ {
1644
+ "completion_length": 257.0,
1645
+ "epoch": 0.002012928395779076,
1646
+ "grad_norm": 3.9375,
1647
+ "kl": 0.0009417292603757232,
1648
+ "learning_rate": 2.0128657397800376e-07,
1649
+ "loss": 0.0,
1650
+ "reward": 2.140402913093567,
1651
+ "reward_std": 0.27203622460365295,
1652
+ "rewards/combined_metrics_reward": 1.5964654088020325,
1653
+ "rewards/reasoning_quality_reward": 0.23900000751018524,
1654
+ "rewards/soft_format_reward_func": 0.0,
1655
+ "rewards/strict_format_reward_func": 0.0,
1656
+ "rewards/xml_structure_reward": 0.0,
1657
+ "rewards/xmlcount_reward_func": 0.3049374893307686,
1658
+ "step": 97
1659
+ },
1660
+ {
1661
+ "completion_length": 169.625,
1662
+ "epoch": 0.002033680234910819,
1663
+ "grad_norm": 4.59375,
1664
+ "kl": 0.0010131081799045205,
1665
+ "learning_rate": 2.0336169329736464e-07,
1666
+ "loss": 0.0,
1667
+ "reward": 3.661734938621521,
1668
+ "reward_std": 0.22614718228578568,
1669
+ "rewards/combined_metrics_reward": 3.0847349166870117,
1670
+ "rewards/reasoning_quality_reward": 0.3280000239610672,
1671
+ "rewards/soft_format_reward_func": 0.0,
1672
+ "rewards/strict_format_reward_func": 0.0,
1673
+ "rewards/xml_structure_reward": 0.0,
1674
+ "rewards/xmlcount_reward_func": 0.2489999756217003,
1675
+ "step": 98
1676
+ },
1677
+ {
1678
+ "completion_length": 113.4375,
1679
+ "epoch": 0.002054432074042562,
1680
+ "grad_norm": 7.875,
1681
+ "kl": 0.0008894397178664804,
1682
+ "learning_rate": 2.0543681261672548e-07,
1683
+ "loss": 0.0,
1684
+ "reward": 3.993846893310547,
1685
+ "reward_std": 0.25242021679878235,
1686
+ "rewards/combined_metrics_reward": 3.385596990585327,
1687
+ "rewards/reasoning_quality_reward": 0.27649999409914017,
1688
+ "rewards/soft_format_reward_func": 0.0,
1689
+ "rewards/strict_format_reward_func": 0.0,
1690
+ "rewards/xml_structure_reward": 0.0,
1691
+ "rewards/xmlcount_reward_func": 0.3317499905824661,
1692
+ "step": 99
1693
+ },
1694
+ {
1695
+ "completion_length": 109.9375,
1696
+ "epoch": 0.0020751839131743052,
1697
+ "grad_norm": 5.71875,
1698
+ "kl": 0.0007490704592783004,
1699
+ "learning_rate": 2.0751193193608637e-07,
1700
+ "loss": 0.0,
1701
+ "reward": 5.884371042251587,
1702
+ "reward_std": 0.22538800537586212,
1703
+ "rewards/combined_metrics_reward": 5.32149600982666,
1704
+ "rewards/reasoning_quality_reward": 0.2524999976158142,
1705
+ "rewards/soft_format_reward_func": 0.0,
1706
+ "rewards/strict_format_reward_func": 0.0,
1707
+ "rewards/xml_structure_reward": 0.0,
1708
+ "rewards/xmlcount_reward_func": 0.31037500500679016,
1709
+ "step": 100
1710
+ }
1711
+ ],
1712
+ "logging_steps": 1,
1713
+ "max_steps": 48188,
1714
+ "num_input_tokens_seen": 0,
1715
+ "num_train_epochs": 1,
1716
+ "save_steps": 100,
1717
+ "stateful_callbacks": {
1718
+ "TrainerControl": {
1719
+ "args": {
1720
+ "should_epoch_stop": false,
1721
+ "should_evaluate": false,
1722
+ "should_log": false,
1723
+ "should_save": true,
1724
+ "should_training_stop": false
1725
+ },
1726
+ "attributes": {}
1727
+ }
1728
+ },
1729
+ "total_flos": 0.0,
1730
+ "train_batch_size": 1,
1731
+ "trial_name": null,
1732
+ "trial_params": null
1733
+ }
Qwen2.5-1.5B-GRPO-Indic-v1/checkpoint-100/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f79c3d19e97fa0dec06a2746daa1e35ada62f6355cd1f722fee98e330f86a83
3
+ size 5624
Qwen2.5-1.5B-GRPO-Indic-v1/checkpoint-100/vocab.json ADDED
The diff for this file is too large to render. See raw diff