Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- all_results.json +8 -0
- config.json +29 -0
- generation_config.json +9 -0
- model.safetensors +3 -0
- special_tokens_map.json +23 -0
- tokenizer.json +3 -0
- tokenizer_config.json +196 -0
- train_results.json +8 -0
- trainer_state.json +1733 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"total_flos": 0.0,
|
3 |
+
"train_loss": 0.014638028192195337,
|
4 |
+
"train_runtime": 22832.117,
|
5 |
+
"train_samples": 11742,
|
6 |
+
"train_samples_per_second": 0.077,
|
7 |
+
"train_steps_per_second": 0.01
|
8 |
+
}
|
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"Qwen2ForCausalLM"
|
4 |
+
],
|
5 |
+
"attention_dropout": 0.0,
|
6 |
+
"bos_token_id": 151643,
|
7 |
+
"eos_token_id": 151643,
|
8 |
+
"hidden_act": "silu",
|
9 |
+
"hidden_size": 1536,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 8960,
|
12 |
+
"max_position_embeddings": 131072,
|
13 |
+
"max_window_layers": 21,
|
14 |
+
"model_type": "qwen2",
|
15 |
+
"num_attention_heads": 12,
|
16 |
+
"num_hidden_layers": 28,
|
17 |
+
"num_key_value_heads": 2,
|
18 |
+
"rms_norm_eps": 1e-06,
|
19 |
+
"rope_scaling": null,
|
20 |
+
"rope_theta": 10000,
|
21 |
+
"sliding_window": 4096,
|
22 |
+
"tie_word_embeddings": false,
|
23 |
+
"torch_dtype": "bfloat16",
|
24 |
+
"transformers_version": "4.50.0.dev0",
|
25 |
+
"use_cache": false,
|
26 |
+
"use_mrope": false,
|
27 |
+
"use_sliding_window": false,
|
28 |
+
"vocab_size": 151936
|
29 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 151646,
|
4 |
+
"do_sample": true,
|
5 |
+
"eos_token_id": 151643,
|
6 |
+
"temperature": 0.6,
|
7 |
+
"top_p": 0.95,
|
8 |
+
"transformers_version": "4.50.0.dev0"
|
9 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5cf6811f62b78ba049e4704a36fe4435c8c5c001eca3898352cbf216a441f049
|
3 |
+
size 3554214752
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|begin▁of▁sentence|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|end▁of▁sentence|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|end▁of▁sentence|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4256422650d141f228fe954acee98679da412984c29a569877eefd3af69315a
|
3 |
+
size 11422959
|
tokenizer_config.json
ADDED
@@ -0,0 +1,196 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"151643": {
|
7 |
+
"content": "<|end▁of▁sentence|>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"151644": {
|
15 |
+
"content": "<|User|>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": false
|
21 |
+
},
|
22 |
+
"151645": {
|
23 |
+
"content": "<|Assistant|>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": false
|
29 |
+
},
|
30 |
+
"151646": {
|
31 |
+
"content": "<|begin▁of▁sentence|>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"151647": {
|
39 |
+
"content": "<|EOT|>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false,
|
44 |
+
"special": false
|
45 |
+
},
|
46 |
+
"151648": {
|
47 |
+
"content": "<think>",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": false,
|
50 |
+
"rstrip": false,
|
51 |
+
"single_word": false,
|
52 |
+
"special": false
|
53 |
+
},
|
54 |
+
"151649": {
|
55 |
+
"content": "</think>",
|
56 |
+
"lstrip": false,
|
57 |
+
"normalized": false,
|
58 |
+
"rstrip": false,
|
59 |
+
"single_word": false,
|
60 |
+
"special": false
|
61 |
+
},
|
62 |
+
"151650": {
|
63 |
+
"content": "<|quad_start|>",
|
64 |
+
"lstrip": false,
|
65 |
+
"normalized": false,
|
66 |
+
"rstrip": false,
|
67 |
+
"single_word": false,
|
68 |
+
"special": true
|
69 |
+
},
|
70 |
+
"151651": {
|
71 |
+
"content": "<|quad_end|>",
|
72 |
+
"lstrip": false,
|
73 |
+
"normalized": false,
|
74 |
+
"rstrip": false,
|
75 |
+
"single_word": false,
|
76 |
+
"special": true
|
77 |
+
},
|
78 |
+
"151652": {
|
79 |
+
"content": "<|vision_start|>",
|
80 |
+
"lstrip": false,
|
81 |
+
"normalized": false,
|
82 |
+
"rstrip": false,
|
83 |
+
"single_word": false,
|
84 |
+
"special": true
|
85 |
+
},
|
86 |
+
"151653": {
|
87 |
+
"content": "<|vision_end|>",
|
88 |
+
"lstrip": false,
|
89 |
+
"normalized": false,
|
90 |
+
"rstrip": false,
|
91 |
+
"single_word": false,
|
92 |
+
"special": true
|
93 |
+
},
|
94 |
+
"151654": {
|
95 |
+
"content": "<|vision_pad|>",
|
96 |
+
"lstrip": false,
|
97 |
+
"normalized": false,
|
98 |
+
"rstrip": false,
|
99 |
+
"single_word": false,
|
100 |
+
"special": true
|
101 |
+
},
|
102 |
+
"151655": {
|
103 |
+
"content": "<|image_pad|>",
|
104 |
+
"lstrip": false,
|
105 |
+
"normalized": false,
|
106 |
+
"rstrip": false,
|
107 |
+
"single_word": false,
|
108 |
+
"special": true
|
109 |
+
},
|
110 |
+
"151656": {
|
111 |
+
"content": "<|video_pad|>",
|
112 |
+
"lstrip": false,
|
113 |
+
"normalized": false,
|
114 |
+
"rstrip": false,
|
115 |
+
"single_word": false,
|
116 |
+
"special": true
|
117 |
+
},
|
118 |
+
"151657": {
|
119 |
+
"content": "<tool_call>",
|
120 |
+
"lstrip": false,
|
121 |
+
"normalized": false,
|
122 |
+
"rstrip": false,
|
123 |
+
"single_word": false,
|
124 |
+
"special": false
|
125 |
+
},
|
126 |
+
"151658": {
|
127 |
+
"content": "</tool_call>",
|
128 |
+
"lstrip": false,
|
129 |
+
"normalized": false,
|
130 |
+
"rstrip": false,
|
131 |
+
"single_word": false,
|
132 |
+
"special": false
|
133 |
+
},
|
134 |
+
"151659": {
|
135 |
+
"content": "<|fim_prefix|>",
|
136 |
+
"lstrip": false,
|
137 |
+
"normalized": false,
|
138 |
+
"rstrip": false,
|
139 |
+
"single_word": false,
|
140 |
+
"special": false
|
141 |
+
},
|
142 |
+
"151660": {
|
143 |
+
"content": "<|fim_middle|>",
|
144 |
+
"lstrip": false,
|
145 |
+
"normalized": false,
|
146 |
+
"rstrip": false,
|
147 |
+
"single_word": false,
|
148 |
+
"special": false
|
149 |
+
},
|
150 |
+
"151661": {
|
151 |
+
"content": "<|fim_suffix|>",
|
152 |
+
"lstrip": false,
|
153 |
+
"normalized": false,
|
154 |
+
"rstrip": false,
|
155 |
+
"single_word": false,
|
156 |
+
"special": false
|
157 |
+
},
|
158 |
+
"151662": {
|
159 |
+
"content": "<|fim_pad|>",
|
160 |
+
"lstrip": false,
|
161 |
+
"normalized": false,
|
162 |
+
"rstrip": false,
|
163 |
+
"single_word": false,
|
164 |
+
"special": false
|
165 |
+
},
|
166 |
+
"151663": {
|
167 |
+
"content": "<|repo_name|>",
|
168 |
+
"lstrip": false,
|
169 |
+
"normalized": false,
|
170 |
+
"rstrip": false,
|
171 |
+
"single_word": false,
|
172 |
+
"special": false
|
173 |
+
},
|
174 |
+
"151664": {
|
175 |
+
"content": "<|file_sep|>",
|
176 |
+
"lstrip": false,
|
177 |
+
"normalized": false,
|
178 |
+
"rstrip": false,
|
179 |
+
"single_word": false,
|
180 |
+
"special": false
|
181 |
+
}
|
182 |
+
},
|
183 |
+
"bos_token": "<|begin▁of▁sentence|>",
|
184 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<|User|>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<|Assistant|><|tool▁calls▁begin|><|tool▁call▁begin��>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<|tool▁call▁end|>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<|tool▁call▁end|>'}}{{'<|tool▁calls▁end|><|end▁of▁sentence|>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<|tool▁outputs▁end|>' + message['content'] + '<|end▁of▁sentence|>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<|Assistant|>' + content + '<|end▁of▁sentence|>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<|tool▁outputs▁begin|><|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<|tool▁outputs▁end|>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<|Assistant|><think>\\n'}}{% endif %}",
|
185 |
+
"clean_up_tokenization_spaces": false,
|
186 |
+
"eos_token": "<|end▁of▁sentence|>",
|
187 |
+
"extra_special_tokens": {},
|
188 |
+
"legacy": true,
|
189 |
+
"model_max_length": 16384,
|
190 |
+
"pad_token": "<|end▁of▁sentence|>",
|
191 |
+
"padding_side": "left",
|
192 |
+
"sp_model_kwargs": {},
|
193 |
+
"tokenizer_class": "LlamaTokenizerFast",
|
194 |
+
"unk_token": null,
|
195 |
+
"use_default_system_prompt": false
|
196 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"total_flos": 0.0,
|
3 |
+
"train_loss": 0.014638028192195337,
|
4 |
+
"train_runtime": 22832.117,
|
5 |
+
"train_samples": 11742,
|
6 |
+
"train_samples_per_second": 0.077,
|
7 |
+
"train_steps_per_second": 0.01
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1733 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_global_step": null,
|
3 |
+
"best_metric": null,
|
4 |
+
"best_model_checkpoint": null,
|
5 |
+
"epoch": 0.15057060126043265,
|
6 |
+
"eval_steps": 100,
|
7 |
+
"global_step": 221,
|
8 |
+
"is_hyper_param_search": false,
|
9 |
+
"is_local_process_zero": true,
|
10 |
+
"is_world_process_zero": true,
|
11 |
+
"log_history": [
|
12 |
+
{
|
13 |
+
"completion_length": 701.7250213623047,
|
14 |
+
"epoch": 0.0013626298756600238,
|
15 |
+
"grad_norm": 0.826935350894928,
|
16 |
+
"kl": 0.0,
|
17 |
+
"learning_rate": 1.7391304347826088e-06,
|
18 |
+
"loss": -0.0,
|
19 |
+
"reward": 3.2898273691534996,
|
20 |
+
"reward_std": 1.2225780645385385,
|
21 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.41482741106301546,
|
22 |
+
"rewards/all-MiniLM-L6-v2": -0.07499999832361937,
|
23 |
+
"rewards/format_reward_beginEndSolutionFormat": 2.0,
|
24 |
+
"rewards/length_reward": 0.9500000029802322,
|
25 |
+
"step": 2
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"completion_length": 832.4125137329102,
|
29 |
+
"epoch": 0.0027252597513200477,
|
30 |
+
"grad_norm": 0.6933600902557373,
|
31 |
+
"kl": 0.00024503469467163086,
|
32 |
+
"learning_rate": 3.4782608695652175e-06,
|
33 |
+
"loss": 0.0,
|
34 |
+
"reward": 3.45002019405365,
|
35 |
+
"reward_std": 1.13982825120911,
|
36 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.4375201063230634,
|
37 |
+
"rewards/all-MiniLM-L6-v2": 0.11249999888241291,
|
38 |
+
"rewards/format_reward_beginEndSolutionFormat": 2.0,
|
39 |
+
"rewards/length_reward": 0.9000000059604645,
|
40 |
+
"step": 4
|
41 |
+
},
|
42 |
+
{
|
43 |
+
"completion_length": 731.8750114440918,
|
44 |
+
"epoch": 0.004087889626980072,
|
45 |
+
"grad_norm": 0.7940042614936829,
|
46 |
+
"kl": 0.0002880692481994629,
|
47 |
+
"learning_rate": 5.2173913043478265e-06,
|
48 |
+
"loss": 0.0,
|
49 |
+
"reward": 2.9608234241604805,
|
50 |
+
"reward_std": 1.052665668539703,
|
51 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.4483234500512481,
|
52 |
+
"rewards/all-MiniLM-L6-v2": -0.3874999973922968,
|
53 |
+
"rewards/format_reward_beginEndSolutionFormat": 2.0,
|
54 |
+
"rewards/length_reward": 0.9000000013038516,
|
55 |
+
"step": 6
|
56 |
+
},
|
57 |
+
{
|
58 |
+
"completion_length": 787.5625152587891,
|
59 |
+
"epoch": 0.005450519502640095,
|
60 |
+
"grad_norm": 0.7262738347053528,
|
61 |
+
"kl": 0.00028836727142333984,
|
62 |
+
"learning_rate": 6.956521739130435e-06,
|
63 |
+
"loss": 0.0,
|
64 |
+
"reward": 2.5098357554525137,
|
65 |
+
"reward_std": 1.7445468110963702,
|
66 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.409835753031075,
|
67 |
+
"rewards/all-MiniLM-L6-v2": -0.4249999960884452,
|
68 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.8499999977648258,
|
69 |
+
"rewards/length_reward": 0.6750000044703484,
|
70 |
+
"step": 8
|
71 |
+
},
|
72 |
+
{
|
73 |
+
"completion_length": 751.5000133514404,
|
74 |
+
"epoch": 0.00681314937830012,
|
75 |
+
"grad_norm": 0.7745183110237122,
|
76 |
+
"kl": 0.0004850625991821289,
|
77 |
+
"learning_rate": 8.695652173913044e-06,
|
78 |
+
"loss": 0.0,
|
79 |
+
"reward": 2.9620843827724457,
|
80 |
+
"reward_std": 1.278110965853557,
|
81 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.47458438016474247,
|
82 |
+
"rewards/all-MiniLM-L6-v2": -0.2749999985098839,
|
83 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.9624999985098839,
|
84 |
+
"rewards/length_reward": 0.8000000091269612,
|
85 |
+
"step": 10
|
86 |
+
},
|
87 |
+
{
|
88 |
+
"completion_length": 744.9250144958496,
|
89 |
+
"epoch": 0.008175779253960144,
|
90 |
+
"grad_norm": 0.7855518460273743,
|
91 |
+
"kl": 0.0019762516021728516,
|
92 |
+
"learning_rate": 1.0434782608695653e-05,
|
93 |
+
"loss": 0.0001,
|
94 |
+
"reward": 2.617582857608795,
|
95 |
+
"reward_std": 1.4501504292711616,
|
96 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.41758283600211143,
|
97 |
+
"rewards/all-MiniLM-L6-v2": -0.49999999813735485,
|
98 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.9249999970197678,
|
99 |
+
"rewards/length_reward": 0.7750000087544322,
|
100 |
+
"step": 12
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"completion_length": 853.975025177002,
|
104 |
+
"epoch": 0.009538409129620166,
|
105 |
+
"grad_norm": 0.7132939100265503,
|
106 |
+
"kl": 0.0023059844970703125,
|
107 |
+
"learning_rate": 1.2173913043478263e-05,
|
108 |
+
"loss": 0.0001,
|
109 |
+
"reward": 3.0857974849641323,
|
110 |
+
"reward_std": 1.1976260086521506,
|
111 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.3857975276187062,
|
112 |
+
"rewards/all-MiniLM-L6-v2": -0.11249999608844519,
|
113 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.9624999985098839,
|
114 |
+
"rewards/length_reward": 0.850000006146729,
|
115 |
+
"step": 14
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"completion_length": 809.7375106811523,
|
119 |
+
"epoch": 0.01090103900528019,
|
120 |
+
"grad_norm": 0.7411205172538757,
|
121 |
+
"kl": 0.0045413970947265625,
|
122 |
+
"learning_rate": 1.391304347826087e-05,
|
123 |
+
"loss": 0.0002,
|
124 |
+
"reward": 3.3214251101017,
|
125 |
+
"reward_std": 0.94907569559291,
|
126 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.40892498986795545,
|
127 |
+
"rewards/all-MiniLM-L6-v2": 0.037500000558793545,
|
128 |
+
"rewards/format_reward_beginEndSolutionFormat": 2.0,
|
129 |
+
"rewards/length_reward": 0.8750000046566129,
|
130 |
+
"step": 16
|
131 |
+
},
|
132 |
+
{
|
133 |
+
"completion_length": 813.1250114440918,
|
134 |
+
"epoch": 0.012263668880940215,
|
135 |
+
"grad_norm": 14.433080673217773,
|
136 |
+
"kl": 0.2021026611328125,
|
137 |
+
"learning_rate": 1.565217391304348e-05,
|
138 |
+
"loss": 0.0081,
|
139 |
+
"reward": 3.0686260610818863,
|
140 |
+
"reward_std": 1.5170891038142145,
|
141 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.48112595453858376,
|
142 |
+
"rewards/all-MiniLM-L6-v2": -0.2374999951571226,
|
143 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.9249999970197678,
|
144 |
+
"rewards/length_reward": 0.9000000059604645,
|
145 |
+
"step": 18
|
146 |
+
},
|
147 |
+
{
|
148 |
+
"completion_length": 754.1750144958496,
|
149 |
+
"epoch": 0.01362629875660024,
|
150 |
+
"grad_norm": 2.9093778133392334,
|
151 |
+
"kl": 0.06426239013671875,
|
152 |
+
"learning_rate": 1.739130434782609e-05,
|
153 |
+
"loss": 0.0026,
|
154 |
+
"reward": 3.807109519839287,
|
155 |
+
"reward_std": 0.7755511063151062,
|
156 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.5696093924343586,
|
157 |
+
"rewards/all-MiniLM-L6-v2": 0.2875000014901161,
|
158 |
+
"rewards/format_reward_beginEndSolutionFormat": 2.0,
|
159 |
+
"rewards/length_reward": 0.9500000029802322,
|
160 |
+
"step": 20
|
161 |
+
},
|
162 |
+
{
|
163 |
+
"completion_length": 758.8125038146973,
|
164 |
+
"epoch": 0.014988928632260262,
|
165 |
+
"grad_norm": 0.8031071424484253,
|
166 |
+
"kl": 0.020557403564453125,
|
167 |
+
"learning_rate": 1.9130434782608697e-05,
|
168 |
+
"loss": 0.0008,
|
169 |
+
"reward": 3.0672582909464836,
|
170 |
+
"reward_std": 0.7253409158438444,
|
171 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.5797582101076841,
|
172 |
+
"rewards/all-MiniLM-L6-v2": -0.46249999944120646,
|
173 |
+
"rewards/format_reward_beginEndSolutionFormat": 2.0,
|
174 |
+
"rewards/length_reward": 0.9500000029802322,
|
175 |
+
"step": 22
|
176 |
+
},
|
177 |
+
{
|
178 |
+
"completion_length": 738.9500198364258,
|
179 |
+
"epoch": 0.016351558507920288,
|
180 |
+
"grad_norm": 0.7532008290290833,
|
181 |
+
"kl": 0.036285400390625,
|
182 |
+
"learning_rate": 1.9998741276738753e-05,
|
183 |
+
"loss": 0.0015,
|
184 |
+
"reward": 3.575051836669445,
|
185 |
+
"reward_std": 0.8001346649834886,
|
186 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6000517811626196,
|
187 |
+
"rewards/all-MiniLM-L6-v2": 0.025000003166496754,
|
188 |
+
"rewards/format_reward_beginEndSolutionFormat": 2.0,
|
189 |
+
"rewards/length_reward": 0.9500000029802322,
|
190 |
+
"step": 24
|
191 |
+
},
|
192 |
+
{
|
193 |
+
"completion_length": 772.2625160217285,
|
194 |
+
"epoch": 0.01771418838358031,
|
195 |
+
"grad_norm": 0.7200579643249512,
|
196 |
+
"kl": 0.08385467529296875,
|
197 |
+
"learning_rate": 1.9988673391830082e-05,
|
198 |
+
"loss": 0.0034,
|
199 |
+
"reward": 3.486709274351597,
|
200 |
+
"reward_std": 1.1654404955916107,
|
201 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.5367092387750745,
|
202 |
+
"rewards/all-MiniLM-L6-v2": 0.02500000409781933,
|
203 |
+
"rewards/format_reward_beginEndSolutionFormat": 2.0,
|
204 |
+
"rewards/length_reward": 0.9250000044703484,
|
205 |
+
"step": 26
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"completion_length": 759.0875091552734,
|
209 |
+
"epoch": 0.019076818259240333,
|
210 |
+
"grad_norm": 0.7885477542877197,
|
211 |
+
"kl": 0.0690155029296875,
|
212 |
+
"learning_rate": 1.9968547759519426e-05,
|
213 |
+
"loss": 0.0028,
|
214 |
+
"reward": 3.937687858939171,
|
215 |
+
"reward_std": 0.8582523697987199,
|
216 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6376878507435322,
|
217 |
+
"rewards/all-MiniLM-L6-v2": 0.4000000022351742,
|
218 |
+
"rewards/format_reward_beginEndSolutionFormat": 2.0,
|
219 |
+
"rewards/length_reward": 0.9000000031664968,
|
220 |
+
"step": 28
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"completion_length": 733.7500076293945,
|
224 |
+
"epoch": 0.020439448134900357,
|
225 |
+
"grad_norm": 0.6713956594467163,
|
226 |
+
"kl": 0.0721435546875,
|
227 |
+
"learning_rate": 1.9938384644612542e-05,
|
228 |
+
"loss": 0.0029,
|
229 |
+
"reward": 3.545550711452961,
|
230 |
+
"reward_std": 1.1149344076402485,
|
231 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.5705506596714258,
|
232 |
+
"rewards/all-MiniLM-L6-v2": 0.0625000037252903,
|
233 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.9624999985098839,
|
234 |
+
"rewards/length_reward": 0.9500000029802322,
|
235 |
+
"step": 30
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"completion_length": 793.4125213623047,
|
239 |
+
"epoch": 0.02180207801056038,
|
240 |
+
"grad_norm": 0.6639223098754883,
|
241 |
+
"kl": 0.06781005859375,
|
242 |
+
"learning_rate": 1.989821441880933e-05,
|
243 |
+
"loss": 0.0027,
|
244 |
+
"reward": 3.9647994488477707,
|
245 |
+
"reward_std": 1.1172373143490404,
|
246 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6397993620485067,
|
247 |
+
"rewards/all-MiniLM-L6-v2": 0.4375,
|
248 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.9624999985098839,
|
249 |
+
"rewards/length_reward": 0.9250000044703484,
|
250 |
+
"step": 32
|
251 |
+
},
|
252 |
+
{
|
253 |
+
"completion_length": 713.4125213623047,
|
254 |
+
"epoch": 0.023164707886220406,
|
255 |
+
"grad_norm": 0.6671966910362244,
|
256 |
+
"kl": 0.0789947509765625,
|
257 |
+
"learning_rate": 1.9848077530122083e-05,
|
258 |
+
"loss": 0.0032,
|
259 |
+
"reward": 4.12811366468668,
|
260 |
+
"reward_std": 0.6696655503474176,
|
261 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6656134920194745,
|
262 |
+
"rewards/all-MiniLM-L6-v2": 0.5125000011175871,
|
263 |
+
"rewards/format_reward_beginEndSolutionFormat": 2.0,
|
264 |
+
"rewards/length_reward": 0.9500000001862645,
|
265 |
+
"step": 34
|
266 |
+
},
|
267 |
+
{
|
268 |
+
"completion_length": 621.1875171661377,
|
269 |
+
"epoch": 0.02452733776188043,
|
270 |
+
"grad_norm": 0.6927969455718994,
|
271 |
+
"kl": 0.100311279296875,
|
272 |
+
"learning_rate": 1.978802446214779e-05,
|
273 |
+
"loss": 0.004,
|
274 |
+
"reward": 3.9949512034654617,
|
275 |
+
"reward_std": 1.0779171623289585,
|
276 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6824510861188173,
|
277 |
+
"rewards/all-MiniLM-L6-v2": 0.3375000050291419,
|
278 |
+
"rewards/format_reward_beginEndSolutionFormat": 2.0,
|
279 |
+
"rewards/length_reward": 0.9750000014901161,
|
280 |
+
"step": 36
|
281 |
+
},
|
282 |
+
{
|
283 |
+
"completion_length": 561.4625148773193,
|
284 |
+
"epoch": 0.025889967637540454,
|
285 |
+
"grad_norm": 0.8079332113265991,
|
286 |
+
"kl": 0.105621337890625,
|
287 |
+
"learning_rate": 1.9718115683235418e-05,
|
288 |
+
"loss": 0.0042,
|
289 |
+
"reward": 3.3487851433455944,
|
290 |
+
"reward_std": 1.0449772235006094,
|
291 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6237850617617369,
|
292 |
+
"rewards/all-MiniLM-L6-v2": -0.049999997951090336,
|
293 |
+
"rewards/format_reward_beginEndSolutionFormat": 2.0,
|
294 |
+
"rewards/length_reward": 0.7750000106170774,
|
295 |
+
"step": 38
|
296 |
+
},
|
297 |
+
{
|
298 |
+
"completion_length": 600.0875129699707,
|
299 |
+
"epoch": 0.02725259751320048,
|
300 |
+
"grad_norm": 0.7116134762763977,
|
301 |
+
"kl": 0.100372314453125,
|
302 |
+
"learning_rate": 1.9638421585599422e-05,
|
303 |
+
"loss": 0.004,
|
304 |
+
"reward": 4.384867042303085,
|
305 |
+
"reward_std": 0.719090289901942,
|
306 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.7348670326173306,
|
307 |
+
"rewards/all-MiniLM-L6-v2": 0.7750000013038516,
|
308 |
+
"rewards/format_reward_beginEndSolutionFormat": 2.0,
|
309 |
+
"rewards/length_reward": 0.8750000074505806,
|
310 |
+
"step": 40
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"completion_length": 598.8750190734863,
|
314 |
+
"epoch": 0.0286152273888605,
|
315 |
+
"grad_norm": 0.7759160399436951,
|
316 |
+
"kl": 0.143280029296875,
|
317 |
+
"learning_rate": 1.9549022414440738e-05,
|
318 |
+
"loss": 0.0057,
|
319 |
+
"reward": 3.826561488211155,
|
320 |
+
"reward_std": 0.9282979969866574,
|
321 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6765614040195942,
|
322 |
+
"rewards/all-MiniLM-L6-v2": 0.2249999986961484,
|
323 |
+
"rewards/format_reward_beginEndSolutionFormat": 2.0,
|
324 |
+
"rewards/length_reward": 0.9250000044703484,
|
325 |
+
"step": 42
|
326 |
+
},
|
327 |
+
{
|
328 |
+
"completion_length": 625.4625110626221,
|
329 |
+
"epoch": 0.029977857264520524,
|
330 |
+
"grad_norm": 0.7551826238632202,
|
331 |
+
"kl": 0.116241455078125,
|
332 |
+
"learning_rate": 1.9450008187146685e-05,
|
333 |
+
"loss": 0.0046,
|
334 |
+
"reward": 4.079624235630035,
|
335 |
+
"reward_std": 1.025521146133542,
|
336 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.7171240504831076,
|
337 |
+
"rewards/all-MiniLM-L6-v2": 0.4375000009313226,
|
338 |
+
"rewards/format_reward_beginEndSolutionFormat": 2.0,
|
339 |
+
"rewards/length_reward": 0.9250000016763806,
|
340 |
+
"step": 44
|
341 |
+
},
|
342 |
+
{
|
343 |
+
"completion_length": 759.9500160217285,
|
344 |
+
"epoch": 0.03134048714018055,
|
345 |
+
"grad_norm": 0.6660957932472229,
|
346 |
+
"kl": 0.10888671875,
|
347 |
+
"learning_rate": 1.9341478602651068e-05,
|
348 |
+
"loss": 0.0044,
|
349 |
+
"reward": 3.9495397955179214,
|
350 |
+
"reward_std": 1.2625608062371612,
|
351 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.7370398119091988,
|
352 |
+
"rewards/all-MiniLM-L6-v2": 0.3625000026077032,
|
353 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.9249999970197678,
|
354 |
+
"rewards/length_reward": 0.9250000016763806,
|
355 |
+
"step": 46
|
356 |
+
},
|
357 |
+
{
|
358 |
+
"completion_length": 826.0875129699707,
|
359 |
+
"epoch": 0.032703117015840576,
|
360 |
+
"grad_norm": 0.6011426448822021,
|
361 |
+
"kl": 0.118682861328125,
|
362 |
+
"learning_rate": 1.9223542941045817e-05,
|
363 |
+
"loss": 0.0047,
|
364 |
+
"reward": 3.5684720501303673,
|
365 |
+
"reward_std": 0.6631585191935301,
|
366 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6809719651937485,
|
367 |
+
"rewards/all-MiniLM-L6-v2": -0.012500000186264515,
|
368 |
+
"rewards/format_reward_beginEndSolutionFormat": 2.0,
|
369 |
+
"rewards/length_reward": 0.9000000031664968,
|
370 |
+
"step": 48
|
371 |
+
},
|
372 |
+
{
|
373 |
+
"completion_length": 938.2875137329102,
|
374 |
+
"epoch": 0.034065746891500596,
|
375 |
+
"grad_norm": 0.6014713048934937,
|
376 |
+
"kl": 0.126922607421875,
|
377 |
+
"learning_rate": 1.9096319953545186e-05,
|
378 |
+
"loss": 0.0051,
|
379 |
+
"reward": 3.5386421233415604,
|
380 |
+
"reward_std": 1.796545386314392,
|
381 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6011420339345932,
|
382 |
+
"rewards/all-MiniLM-L6-v2": 0.4000000022351742,
|
383 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.8124999925494194,
|
384 |
+
"rewards/length_reward": 0.7250000089406967,
|
385 |
+
"step": 50
|
386 |
+
},
|
387 |
+
{
|
388 |
+
"completion_length": 936.8000183105469,
|
389 |
+
"epoch": 0.03542837676716062,
|
390 |
+
"grad_norm": 0.623587429523468,
|
391 |
+
"kl": 0.138763427734375,
|
392 |
+
"learning_rate": 1.895993774291336e-05,
|
393 |
+
"loss": 0.0056,
|
394 |
+
"reward": 3.6302099227905273,
|
395 |
+
"reward_std": 1.3007243419997394,
|
396 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6302098724991083,
|
397 |
+
"rewards/all-MiniLM-L6-v2": 0.3375000022351742,
|
398 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.9624999985098839,
|
399 |
+
"rewards/length_reward": 0.7000000076368451,
|
400 |
+
"step": 52
|
401 |
+
},
|
402 |
+
{
|
403 |
+
"completion_length": 774.3875160217285,
|
404 |
+
"epoch": 0.036791006642820645,
|
405 |
+
"grad_norm": 0.5999850630760193,
|
406 |
+
"kl": 0.15771484375,
|
407 |
+
"learning_rate": 1.881453363447582e-05,
|
408 |
+
"loss": 0.0063,
|
409 |
+
"reward": 4.047312401235104,
|
410 |
+
"reward_std": 0.8825826905667782,
|
411 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6848122831434011,
|
412 |
+
"rewards/all-MiniLM-L6-v2": 0.4125000024214387,
|
413 |
+
"rewards/format_reward_beginEndSolutionFormat": 2.0,
|
414 |
+
"rewards/length_reward": 0.9500000029802322,
|
415 |
+
"step": 54
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"completion_length": 664.0375175476074,
|
419 |
+
"epoch": 0.038153636518480666,
|
420 |
+
"grad_norm": 0.6805257201194763,
|
421 |
+
"kl": 0.1588134765625,
|
422 |
+
"learning_rate": 1.866025403784439e-05,
|
423 |
+
"loss": 0.0064,
|
424 |
+
"reward": 3.92198596149683,
|
425 |
+
"reward_std": 0.7282474122475833,
|
426 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6469858698546886,
|
427 |
+
"rewards/all-MiniLM-L6-v2": 0.34999999962747097,
|
428 |
+
"rewards/format_reward_beginEndSolutionFormat": 2.0,
|
429 |
+
"rewards/length_reward": 0.9250000016763806,
|
430 |
+
"step": 56
|
431 |
+
},
|
432 |
+
{
|
433 |
+
"completion_length": 702.6375160217285,
|
434 |
+
"epoch": 0.039516266394140694,
|
435 |
+
"grad_norm": 0.7188987135887146,
|
436 |
+
"kl": 0.14849853515625,
|
437 |
+
"learning_rate": 1.8497254299495147e-05,
|
438 |
+
"loss": 0.0059,
|
439 |
+
"reward": 3.4211702197790146,
|
440 |
+
"reward_std": 1.4494188777171075,
|
441 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.5586702147556935,
|
442 |
+
"rewards/all-MiniLM-L6-v2": 0.2875000052154064,
|
443 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.8499999977648258,
|
444 |
+
"rewards/length_reward": 0.725000006146729,
|
445 |
+
"step": 58
|
446 |
+
},
|
447 |
+
{
|
448 |
+
"completion_length": 641.7625064849854,
|
449 |
+
"epoch": 0.040878896269800714,
|
450 |
+
"grad_norm": 0.9523748159408569,
|
451 |
+
"kl": 0.1611328125,
|
452 |
+
"learning_rate": 1.8325698546347714e-05,
|
453 |
+
"loss": 0.0064,
|
454 |
+
"reward": 3.841396249830723,
|
455 |
+
"reward_std": 1.1254777936264873,
|
456 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6538961809128523,
|
457 |
+
"rewards/all-MiniLM-L6-v2": 0.43750000186264515,
|
458 |
+
"rewards/format_reward_beginEndSolutionFormat": 2.0,
|
459 |
+
"rewards/length_reward": 0.7500000093132257,
|
460 |
+
"step": 60
|
461 |
+
},
|
462 |
+
{
|
463 |
+
"completion_length": 704.0375175476074,
|
464 |
+
"epoch": 0.04224152614546074,
|
465 |
+
"grad_norm": 0.7048397064208984,
|
466 |
+
"kl": 0.164093017578125,
|
467 |
+
"learning_rate": 1.814575952050336e-05,
|
468 |
+
"loss": 0.0066,
|
469 |
+
"reward": 3.5937935784459114,
|
470 |
+
"reward_std": 1.1683010547421873,
|
471 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.71879349835217,
|
472 |
+
"rewards/all-MiniLM-L6-v2": 0.13750000018626451,
|
473 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.9624999985098839,
|
474 |
+
"rewards/length_reward": 0.7750000059604645,
|
475 |
+
"step": 62
|
476 |
+
},
|
477 |
+
{
|
478 |
+
"completion_length": 609.1125087738037,
|
479 |
+
"epoch": 0.04360415602112076,
|
480 |
+
"grad_norm": 0.8203504085540771,
|
481 |
+
"kl": 0.178314208984375,
|
482 |
+
"learning_rate": 1.7957618405308323e-05,
|
483 |
+
"loss": 0.0071,
|
484 |
+
"reward": 3.6722382232546806,
|
485 |
+
"reward_std": 1.1893206317909062,
|
486 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6222381666302681,
|
487 |
+
"rewards/all-MiniLM-L6-v2": 0.3000000035390258,
|
488 |
+
"rewards/format_reward_beginEndSolutionFormat": 2.0,
|
489 |
+
"rewards/length_reward": 0.7500000093132257,
|
490 |
+
"step": 64
|
491 |
+
},
|
492 |
+
{
|
493 |
+
"completion_length": 640.1500129699707,
|
494 |
+
"epoch": 0.044966785896780784,
|
495 |
+
"grad_norm": 0.7613713145256042,
|
496 |
+
"kl": 0.1834259033203125,
|
497 |
+
"learning_rate": 1.776146464291757e-05,
|
498 |
+
"loss": 0.0073,
|
499 |
+
"reward": 4.024308562278748,
|
500 |
+
"reward_std": 1.0513806878589094,
|
501 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6868084445595741,
|
502 |
+
"rewards/all-MiniLM-L6-v2": 0.3624999988824129,
|
503 |
+
"rewards/format_reward_beginEndSolutionFormat": 2.0,
|
504 |
+
"rewards/length_reward": 0.9750000014901161,
|
505 |
+
"step": 66
|
506 |
+
},
|
507 |
+
{
|
508 |
+
"completion_length": 793.487512588501,
|
509 |
+
"epoch": 0.04632941577244081,
|
510 |
+
"grad_norm": 0.7231267094612122,
|
511 |
+
"kl": 0.26812744140625,
|
512 |
+
"learning_rate": 1.7557495743542586e-05,
|
513 |
+
"loss": 0.0107,
|
514 |
+
"reward": 2.855987273156643,
|
515 |
+
"reward_std": 1.688657500082627,
|
516 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6434871796518564,
|
517 |
+
"rewards/all-MiniLM-L6-v2": -0.012499998323619366,
|
518 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.8499999986961484,
|
519 |
+
"rewards/length_reward": 0.3750000046566129,
|
520 |
+
"step": 68
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"completion_length": 789.1500263214111,
|
524 |
+
"epoch": 0.04769204564810083,
|
525 |
+
"grad_norm": 0.9249826669692993,
|
526 |
+
"kl": 0.33258056640625,
|
527 |
+
"learning_rate": 1.734591708657533e-05,
|
528 |
+
"loss": 0.0133,
|
529 |
+
"reward": 2.242995586246252,
|
530 |
+
"reward_std": 2.346400245092809,
|
531 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.5554955210536718,
|
532 |
+
"rewards/all-MiniLM-L6-v2": -0.19999999832361937,
|
533 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.6624999940395355,
|
534 |
+
"rewards/length_reward": 0.22500000149011612,
|
535 |
+
"step": 70
|
536 |
+
},
|
537 |
+
{
|
538 |
+
"completion_length": 702.3250160217285,
|
539 |
+
"epoch": 0.04905467552376086,
|
540 |
+
"grad_norm": 1.8796899318695068,
|
541 |
+
"kl": 0.3321533203125,
|
542 |
+
"learning_rate": 1.7126941713788633e-05,
|
543 |
+
"loss": 0.0133,
|
544 |
+
"reward": 3.2902688309550285,
|
545 |
+
"reward_std": 1.93663672497496,
|
546 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.7652687635272741,
|
547 |
+
"rewards/all-MiniLM-L6-v2": 0.17500000167638063,
|
548 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.8500000014901161,
|
549 |
+
"rewards/length_reward": 0.500000006519258,
|
550 |
+
"step": 72
|
551 |
+
},
|
552 |
+
{
|
553 |
+
"completion_length": 796.2000179290771,
|
554 |
+
"epoch": 0.05041730539942088,
|
555 |
+
"grad_norm": 1.0197867155075073,
|
556 |
+
"kl": 0.45782470703125,
|
557 |
+
"learning_rate": 1.6900790114821122e-05,
|
558 |
+
"loss": 0.0183,
|
559 |
+
"reward": 2.451604187488556,
|
560 |
+
"reward_std": 2.372755976160988,
|
561 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6391041371971369,
|
562 |
+
"rewards/all-MiniLM-L6-v2": 0.10000000335276127,
|
563 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.3624999970197678,
|
564 |
+
"rewards/length_reward": 0.35000001080334187,
|
565 |
+
"step": 74
|
566 |
+
},
|
567 |
+
{
|
568 |
+
"completion_length": 716.0625038146973,
|
569 |
+
"epoch": 0.05177993527508091,
|
570 |
+
"grad_norm": 1.0521018505096436,
|
571 |
+
"kl": 0.38922119140625,
|
572 |
+
"learning_rate": 1.666769000516292e-05,
|
573 |
+
"loss": 0.0156,
|
574 |
+
"reward": 3.2886771922931075,
|
575 |
+
"reward_std": 2.0216886228881776,
|
576 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.7261771578341722,
|
577 |
+
"rewards/all-MiniLM-L6-v2": 0.17500000074505806,
|
578 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.737500000745058,
|
579 |
+
"rewards/length_reward": 0.6500000106170774,
|
580 |
+
"step": 76
|
581 |
+
},
|
582 |
+
{
|
583 |
+
"completion_length": 835.2875137329102,
|
584 |
+
"epoch": 0.05314256515074093,
|
585 |
+
"grad_norm": 1.5486301183700562,
|
586 |
+
"kl": 0.5540771484375,
|
587 |
+
"learning_rate": 1.6427876096865394e-05,
|
588 |
+
"loss": 0.0222,
|
589 |
+
"reward": 2.288073843345046,
|
590 |
+
"reward_std": 2.585562598425895,
|
591 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6880737878382206,
|
592 |
+
"rewards/all-MiniLM-L6-v2": -0.16250000149011612,
|
593 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.2875000014901161,
|
594 |
+
"rewards/length_reward": 0.47500000335276127,
|
595 |
+
"step": 78
|
596 |
+
},
|
597 |
+
{
|
598 |
+
"completion_length": 842.4875106811523,
|
599 |
+
"epoch": 0.05450519502640096,
|
600 |
+
"grad_norm": 0.7873005867004395,
|
601 |
+
"kl": 0.5556640625,
|
602 |
+
"learning_rate": 1.6181589862206053e-05,
|
603 |
+
"loss": 0.0222,
|
604 |
+
"reward": 2.895622299052775,
|
605 |
+
"reward_std": 2.1268671478610486,
|
606 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.570622275583446,
|
607 |
+
"rewards/all-MiniLM-L6-v2": 0.10000000428408384,
|
608 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.7749999910593033,
|
609 |
+
"rewards/length_reward": 0.45000000298023224,
|
610 |
+
"step": 80
|
611 |
+
},
|
612 |
+
{
|
613 |
+
"completion_length": 866.9500141143799,
|
614 |
+
"epoch": 0.05586782490206098,
|
615 |
+
"grad_norm": 0.8428084254264832,
|
616 |
+
"kl": 0.599456787109375,
|
617 |
+
"learning_rate": 1.5929079290546408e-05,
|
618 |
+
"loss": 0.024,
|
619 |
+
"reward": 2.1291475765174255,
|
620 |
+
"reward_std": 2.3366958047263324,
|
621 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.5416475932579488,
|
622 |
+
"rewards/all-MiniLM-L6-v2": -0.3124999953433871,
|
623 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.6249999925494194,
|
624 |
+
"rewards/length_reward": 0.27500000316649675,
|
625 |
+
"step": 82
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"completion_length": 709.7125110626221,
|
629 |
+
"epoch": 0.057230454777721,
|
630 |
+
"grad_norm": 0.714391827583313,
|
631 |
+
"kl": 0.534912109375,
|
632 |
+
"learning_rate": 1.5670598638627707e-05,
|
633 |
+
"loss": 0.0214,
|
634 |
+
"reward": 2.692725880071521,
|
635 |
+
"reward_std": 2.575832322239876,
|
636 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6302258470095694,
|
637 |
+
"rewards/all-MiniLM-L6-v2": 0.10000000428408384,
|
638 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.662499994970858,
|
639 |
+
"rewards/length_reward": 0.30000000447034836,
|
640 |
+
"step": 84
|
641 |
+
},
|
642 |
+
{
|
643 |
+
"completion_length": 653.9125118255615,
|
644 |
+
"epoch": 0.058593084653381027,
|
645 |
+
"grad_norm": 2.24059796333313,
|
646 |
+
"kl": 0.57843017578125,
|
647 |
+
"learning_rate": 1.5406408174555978e-05,
|
648 |
+
"loss": 0.0232,
|
649 |
+
"reward": 2.6488085128366947,
|
650 |
+
"reward_std": 2.0597222729120404,
|
651 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6988084595650434,
|
652 |
+
"rewards/all-MiniLM-L6-v2": -0.050000001676380634,
|
653 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.6999999955296516,
|
654 |
+
"rewards/length_reward": 0.30000000540167093,
|
655 |
+
"step": 86
|
656 |
+
},
|
657 |
+
{
|
658 |
+
"completion_length": 530.4875144958496,
|
659 |
+
"epoch": 0.05995571452904105,
|
660 |
+
"grad_norm": 0.9869608283042908,
|
661 |
+
"kl": 0.4842529296875,
|
662 |
+
"learning_rate": 1.5136773915734067e-05,
|
663 |
+
"loss": 0.0194,
|
664 |
+
"reward": 3.0965824760496616,
|
665 |
+
"reward_std": 1.8650478832423687,
|
666 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.7215823549777269,
|
667 |
+
"rewards/all-MiniLM-L6-v2": 0.3625000035390258,
|
668 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.8124999925494194,
|
669 |
+
"rewards/length_reward": 0.2000000076368451,
|
670 |
+
"step": 88
|
671 |
+
},
|
672 |
+
{
|
673 |
+
"completion_length": 572.0000076293945,
|
674 |
+
"epoch": 0.061318344404701075,
|
675 |
+
"grad_norm": 0.7383394241333008,
|
676 |
+
"kl": 0.4207763671875,
|
677 |
+
"learning_rate": 1.4861967361004687e-05,
|
678 |
+
"loss": 0.0168,
|
679 |
+
"reward": 2.8489164412021637,
|
680 |
+
"reward_std": 2.041708583943546,
|
681 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6489164028316736,
|
682 |
+
"rewards/all-MiniLM-L6-v2": -0.04999999701976776,
|
683 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.7749999947845936,
|
684 |
+
"rewards/length_reward": 0.4750000089406967,
|
685 |
+
"step": 90
|
686 |
+
},
|
687 |
+
{
|
688 |
+
"completion_length": 643.6000156402588,
|
689 |
+
"epoch": 0.0626809742803611,
|
690 |
+
"grad_norm": 0.7305729389190674,
|
691 |
+
"kl": 0.417236328125,
|
692 |
+
"learning_rate": 1.4582265217274105e-05,
|
693 |
+
"loss": 0.0167,
|
694 |
+
"reward": 3.1850010380148888,
|
695 |
+
"reward_std": 1.72700658114627,
|
696 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6975009143352509,
|
697 |
+
"rewards/all-MiniLM-L6-v2": 0.22499999962747097,
|
698 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.6624999977648258,
|
699 |
+
"rewards/length_reward": 0.6000000089406967,
|
700 |
+
"step": 92
|
701 |
+
},
|
702 |
+
{
|
703 |
+
"completion_length": 843.2000122070312,
|
704 |
+
"epoch": 0.06404360415602112,
|
705 |
+
"grad_norm": 0.5814893841743469,
|
706 |
+
"kl": 0.44672393798828125,
|
707 |
+
"learning_rate": 1.4297949120891718e-05,
|
708 |
+
"loss": 0.0179,
|
709 |
+
"reward": 2.340944491326809,
|
710 |
+
"reward_std": 2.093850734643638,
|
711 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6159445056691766,
|
712 |
+
"rewards/all-MiniLM-L6-v2": -0.31249999813735485,
|
713 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.5124999964609742,
|
714 |
+
"rewards/length_reward": 0.5250000022351742,
|
715 |
+
"step": 94
|
716 |
+
},
|
717 |
+
{
|
718 |
+
"completion_length": 767.9875068664551,
|
719 |
+
"epoch": 0.06540623403168115,
|
720 |
+
"grad_norm": 0.5642020106315613,
|
721 |
+
"kl": 0.41064453125,
|
722 |
+
"learning_rate": 1.4009305354066138e-05,
|
723 |
+
"loss": 0.0164,
|
724 |
+
"reward": 3.0814263820648193,
|
725 |
+
"reward_std": 2.0845829099416733,
|
726 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.7064263448119164,
|
727 |
+
"rewards/all-MiniLM-L6-v2": 0.07499999925494194,
|
728 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.625,
|
729 |
+
"rewards/length_reward": 0.6750000054016709,
|
730 |
+
"step": 96
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"completion_length": 732.2500190734863,
|
734 |
+
"epoch": 0.06676886390734117,
|
735 |
+
"grad_norm": 0.6293222904205322,
|
736 |
+
"kl": 0.4149169921875,
|
737 |
+
"learning_rate": 1.3716624556603275e-05,
|
738 |
+
"loss": 0.0166,
|
739 |
+
"reward": 3.167923970380798,
|
740 |
+
"reward_std": 1.9076070357114077,
|
741 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6679238956421614,
|
742 |
+
"rewards/all-MiniLM-L6-v2": 0.12500000093132257,
|
743 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.6999999955296516,
|
744 |
+
"rewards/length_reward": 0.6750000091269612,
|
745 |
+
"step": 98
|
746 |
+
},
|
747 |
+
{
|
748 |
+
"completion_length": 770.9750061035156,
|
749 |
+
"epoch": 0.06813149378300119,
|
750 |
+
"grad_norm": 0.608492910861969,
|
751 |
+
"kl": 0.38108062744140625,
|
752 |
+
"learning_rate": 1.342020143325669e-05,
|
753 |
+
"loss": 0.0153,
|
754 |
+
"reward": 2.9613163992762566,
|
755 |
+
"reward_std": 1.8579347440972924,
|
756 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6363163664937019,
|
757 |
+
"rewards/all-MiniLM-L6-v2": -0.049999997951090336,
|
758 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.8499999977648258,
|
759 |
+
"rewards/length_reward": 0.5250000059604645,
|
760 |
+
"step": 100
|
761 |
+
},
|
762 |
+
{
|
763 |
+
"epoch": 0.06813149378300119,
|
764 |
+
"eval_completion_length": 719.5635530948639,
|
765 |
+
"eval_kl": 0.42165565490722656,
|
766 |
+
"eval_loss": 0.01686381734907627,
|
767 |
+
"eval_reward": 3.1516319193760864,
|
768 |
+
"eval_reward_std": 1.9167220215313137,
|
769 |
+
"eval_rewards/AnswerChecker_LenCheck_Reward": 0.6703818460227922,
|
770 |
+
"eval_rewards/all-MiniLM-L6-v2": 0.06250000081490725,
|
771 |
+
"eval_rewards/format_reward_beginEndSolutionFormat": 1.7374999963212758,
|
772 |
+
"eval_rewards/length_reward": 0.6812500089872628,
|
773 |
+
"eval_runtime": 1234.6422,
|
774 |
+
"eval_samples_per_second": 0.104,
|
775 |
+
"eval_steps_per_second": 0.021,
|
776 |
+
"step": 100
|
777 |
+
},
|
778 |
+
{
|
779 |
+
"completion_length": 708.6000080108643,
|
780 |
+
"epoch": 0.06949412365866121,
|
781 |
+
"grad_norm": 0.5848133563995361,
|
782 |
+
"kl": 0.41204833984375,
|
783 |
+
"learning_rate": 1.3120334456984871e-05,
|
784 |
+
"loss": 0.0165,
|
785 |
+
"reward": 3.301197201013565,
|
786 |
+
"reward_std": 2.1839559585787356,
|
787 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6011971952393651,
|
788 |
+
"rewards/all-MiniLM-L6-v2": 0.24999999906867743,
|
789 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.699999988079071,
|
790 |
+
"rewards/length_reward": 0.7500000093132257,
|
791 |
+
"step": 102
|
792 |
+
},
|
793 |
+
{
|
794 |
+
"completion_length": 660.3000183105469,
|
795 |
+
"epoch": 0.07085675353432123,
|
796 |
+
"grad_norm": 1.3479467630386353,
|
797 |
+
"kl": 0.50341796875,
|
798 |
+
"learning_rate": 1.2817325568414299e-05,
|
799 |
+
"loss": 0.0201,
|
800 |
+
"reward": 2.9223585426807404,
|
801 |
+
"reward_std": 1.763994950801134,
|
802 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6473584100604057,
|
803 |
+
"rewards/all-MiniLM-L6-v2": -0.17499999701976776,
|
804 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.7749999985098839,
|
805 |
+
"rewards/length_reward": 0.6750000081956387,
|
806 |
+
"step": 104
|
807 |
+
},
|
808 |
+
{
|
809 |
+
"completion_length": 684.8875122070312,
|
810 |
+
"epoch": 0.07221938340998127,
|
811 |
+
"grad_norm": 0.6432397365570068,
|
812 |
+
"kl": 0.3974609375,
|
813 |
+
"learning_rate": 1.2511479871810792e-05,
|
814 |
+
"loss": 0.0159,
|
815 |
+
"reward": 3.2463276791386306,
|
816 |
+
"reward_std": 1.709463362582028,
|
817 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6588275767862797,
|
818 |
+
"rewards/all-MiniLM-L6-v2": 0.02500000037252903,
|
819 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.8124999925494194,
|
820 |
+
"rewards/length_reward": 0.7500000046566129,
|
821 |
+
"step": 106
|
822 |
+
},
|
823 |
+
{
|
824 |
+
"completion_length": 671.6875095367432,
|
825 |
+
"epoch": 0.07358201328564129,
|
826 |
+
"grad_norm": 0.6950499415397644,
|
827 |
+
"kl": 0.41790771484375,
|
828 |
+
"learning_rate": 1.2203105327865407e-05,
|
829 |
+
"loss": 0.0167,
|
830 |
+
"reward": 3.2045797668397427,
|
831 |
+
"reward_std": 1.9101572453510016,
|
832 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.7170797474682331,
|
833 |
+
"rewards/all-MiniLM-L6-v2": 0.14999999944120646,
|
834 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.6624999986961484,
|
835 |
+
"rewards/length_reward": 0.6750000072643161,
|
836 |
+
"step": 108
|
837 |
+
},
|
838 |
+
{
|
839 |
+
"completion_length": 808.1000099182129,
|
840 |
+
"epoch": 0.07494464316130131,
|
841 |
+
"grad_norm": 0.5721182227134705,
|
842 |
+
"kl": 0.511962890625,
|
843 |
+
"learning_rate": 1.1892512443604103e-05,
|
844 |
+
"loss": 0.0205,
|
845 |
+
"reward": 2.2793450676836073,
|
846 |
+
"reward_std": 2.890487961471081,
|
847 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6168450396507978,
|
848 |
+
"rewards/all-MiniLM-L6-v2": -0.3124999972060323,
|
849 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.5499999970197678,
|
850 |
+
"rewards/length_reward": 0.4250000100582838,
|
851 |
+
"step": 110
|
852 |
+
},
|
853 |
+
{
|
854 |
+
"completion_length": 693.9000129699707,
|
855 |
+
"epoch": 0.07630727303696133,
|
856 |
+
"grad_norm": 0.5843067765235901,
|
857 |
+
"kl": 0.41845703125,
|
858 |
+
"learning_rate": 1.15800139597335e-05,
|
859 |
+
"loss": 0.0167,
|
860 |
+
"reward": 3.066192142665386,
|
861 |
+
"reward_std": 2.348536633886397,
|
862 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6661920826882124,
|
863 |
+
"rewards/all-MiniLM-L6-v2": -0.01249999925494194,
|
864 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.7374999895691872,
|
865 |
+
"rewards/length_reward": 0.675000011920929,
|
866 |
+
"step": 112
|
867 |
+
},
|
868 |
+
{
|
869 |
+
"completion_length": 868.7250137329102,
|
870 |
+
"epoch": 0.07766990291262135,
|
871 |
+
"grad_norm": 0.5749533772468567,
|
872 |
+
"kl": 0.63037109375,
|
873 |
+
"learning_rate": 1.1265924535737494e-05,
|
874 |
+
"loss": 0.0252,
|
875 |
+
"reward": 1.36430923640728,
|
876 |
+
"reward_std": 3.1500269323587418,
|
877 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.514309162274003,
|
878 |
+
"rewards/all-MiniLM-L6-v2": -0.6499999975785613,
|
879 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.0999999940395355,
|
880 |
+
"rewards/length_reward": 0.4000000050291419,
|
881 |
+
"step": 114
|
882 |
+
},
|
883 |
+
{
|
884 |
+
"completion_length": 725.7375068664551,
|
885 |
+
"epoch": 0.07903253278828139,
|
886 |
+
"grad_norm": 0.5346440672874451,
|
887 |
+
"kl": 0.4619140625,
|
888 |
+
"learning_rate": 1.0950560433041825e-05,
|
889 |
+
"loss": 0.0185,
|
890 |
+
"reward": 2.963149979710579,
|
891 |
+
"reward_std": 2.0242148893885314,
|
892 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6506498479284346,
|
893 |
+
"rewards/all-MiniLM-L6-v2": -0.16249999776482582,
|
894 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.8499999940395355,
|
895 |
+
"rewards/length_reward": 0.6250000093132257,
|
896 |
+
"step": 116
|
897 |
+
},
|
898 |
+
{
|
899 |
+
"completion_length": 773.3750152587891,
|
900 |
+
"epoch": 0.08039516266394141,
|
901 |
+
"grad_norm": 0.6365153193473816,
|
902 |
+
"kl": 0.4718017578125,
|
903 |
+
"learning_rate": 1.0634239196565646e-05,
|
904 |
+
"loss": 0.0189,
|
905 |
+
"reward": 2.2029636511579156,
|
906 |
+
"reward_std": 2.7039426697883755,
|
907 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6029636058956385,
|
908 |
+
"rewards/all-MiniLM-L6-v2": -0.3499999986961484,
|
909 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.474999993108213,
|
910 |
+
"rewards/length_reward": 0.4750000098720193,
|
911 |
+
"step": 118
|
912 |
+
},
|
913 |
+
{
|
914 |
+
"completion_length": 775.962516784668,
|
915 |
+
"epoch": 0.08175779253960143,
|
916 |
+
"grad_norm": 0.5627033710479736,
|
917 |
+
"kl": 0.5267333984375,
|
918 |
+
"learning_rate": 1.031727933498068e-05,
|
919 |
+
"loss": 0.0211,
|
920 |
+
"reward": 2.5474718529731035,
|
921 |
+
"reward_std": 2.10833885287866,
|
922 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6349717965349555,
|
923 |
+
"rewards/all-MiniLM-L6-v2": -0.27499999944120646,
|
924 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.6624999940395355,
|
925 |
+
"rewards/length_reward": 0.5250000078231096,
|
926 |
+
"step": 120
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"completion_length": 641.2125091552734,
|
930 |
+
"epoch": 0.08312042241526145,
|
931 |
+
"grad_norm": 0.5676293969154358,
|
932 |
+
"kl": 0.413330078125,
|
933 |
+
"learning_rate": 1e-05,
|
934 |
+
"loss": 0.0165,
|
935 |
+
"reward": 3.1914120875298977,
|
936 |
+
"reward_std": 1.7586256829090416,
|
937 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.7289120629429817,
|
938 |
+
"rewards/all-MiniLM-L6-v2": -0.11249999981373549,
|
939 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.8499999940395355,
|
940 |
+
"rewards/length_reward": 0.7250000108033419,
|
941 |
+
"step": 122
|
942 |
+
},
|
943 |
+
{
|
944 |
+
"completion_length": 708.8875179290771,
|
945 |
+
"epoch": 0.08448305229092148,
|
946 |
+
"grad_norm": 0.6845495700836182,
|
947 |
+
"kl": 0.5447998046875,
|
948 |
+
"learning_rate": 9.682720665019325e-06,
|
949 |
+
"loss": 0.0218,
|
950 |
+
"reward": 2.7032833639532328,
|
951 |
+
"reward_std": 2.0250429082661867,
|
952 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6782832983881235,
|
953 |
+
"rewards/all-MiniLM-L6-v2": -0.125,
|
954 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.6249999962747097,
|
955 |
+
"rewards/length_reward": 0.5250000078231096,
|
956 |
+
"step": 124
|
957 |
+
},
|
958 |
+
{
|
959 |
+
"completion_length": 693.4625110626221,
|
960 |
+
"epoch": 0.0858456821665815,
|
961 |
+
"grad_norm": 0.7195069193840027,
|
962 |
+
"kl": 0.4825439453125,
|
963 |
+
"learning_rate": 9.365760803434356e-06,
|
964 |
+
"loss": 0.0193,
|
965 |
+
"reward": 2.8621206106618047,
|
966 |
+
"reward_std": 2.122805818915367,
|
967 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6871205642819405,
|
968 |
+
"rewards/all-MiniLM-L6-v2": -0.19999999832361937,
|
969 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.7749999947845936,
|
970 |
+
"rewards/length_reward": 0.6000000080093741,
|
971 |
+
"step": 126
|
972 |
+
},
|
973 |
+
{
|
974 |
+
"completion_length": 716.3250122070312,
|
975 |
+
"epoch": 0.08720831204224153,
|
976 |
+
"grad_norm": 0.678680419921875,
|
977 |
+
"kl": 0.4881591796875,
|
978 |
+
"learning_rate": 9.049439566958176e-06,
|
979 |
+
"loss": 0.0195,
|
980 |
+
"reward": 3.0072994977235794,
|
981 |
+
"reward_std": 2.460042350925505,
|
982 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6822993978857994,
|
983 |
+
"rewards/all-MiniLM-L6-v2": -0.012499997392296791,
|
984 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.6624999903142452,
|
985 |
+
"rewards/length_reward": 0.6750000109896064,
|
986 |
+
"step": 128
|
987 |
+
},
|
988 |
+
{
|
989 |
+
"completion_length": 656.1500129699707,
|
990 |
+
"epoch": 0.08857094191790155,
|
991 |
+
"grad_norm": 0.49265533685684204,
|
992 |
+
"kl": 0.39990234375,
|
993 |
+
"learning_rate": 8.734075464262507e-06,
|
994 |
+
"loss": 0.016,
|
995 |
+
"reward": 3.324027754366398,
|
996 |
+
"reward_std": 1.9725347934290767,
|
997 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.7615277506411076,
|
998 |
+
"rewards/all-MiniLM-L6-v2": 1.862645149230957e-09,
|
999 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.7374999932944775,
|
1000 |
+
"rewards/length_reward": 0.8250000104308128,
|
1001 |
+
"step": 130
|
1002 |
+
},
|
1003 |
+
{
|
1004 |
+
"completion_length": 780.5625152587891,
|
1005 |
+
"epoch": 0.08993357179356157,
|
1006 |
+
"grad_norm": 0.5680932402610779,
|
1007 |
+
"kl": 0.452880859375,
|
1008 |
+
"learning_rate": 8.419986040266502e-06,
|
1009 |
+
"loss": 0.0181,
|
1010 |
+
"reward": 3.1687414944171906,
|
1011 |
+
"reward_std": 2.452119631692767,
|
1012 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6687414180487394,
|
1013 |
+
"rewards/all-MiniLM-L6-v2": 0.25,
|
1014 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.624999988824129,
|
1015 |
+
"rewards/length_reward": 0.625000006519258,
|
1016 |
+
"step": 132
|
1017 |
+
},
|
1018 |
+
{
|
1019 |
+
"completion_length": 787.3375110626221,
|
1020 |
+
"epoch": 0.0912962016692216,
|
1021 |
+
"grad_norm": 0.5462779998779297,
|
1022 |
+
"kl": 0.43536376953125,
|
1023 |
+
"learning_rate": 8.107487556395902e-06,
|
1024 |
+
"loss": 0.0174,
|
1025 |
+
"reward": 2.4839657694101334,
|
1026 |
+
"reward_std": 2.853791818022728,
|
1027 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6589657235890627,
|
1028 |
+
"rewards/all-MiniLM-L6-v2": -0.2625000011175871,
|
1029 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.5124999964609742,
|
1030 |
+
"rewards/length_reward": 0.5750000094994903,
|
1031 |
+
"step": 134
|
1032 |
+
},
|
1033 |
+
{
|
1034 |
+
"completion_length": 820.3000240325928,
|
1035 |
+
"epoch": 0.09265883154488162,
|
1036 |
+
"grad_norm": 0.5613769292831421,
|
1037 |
+
"kl": 0.524169921875,
|
1038 |
+
"learning_rate": 7.796894672134594e-06,
|
1039 |
+
"loss": 0.021,
|
1040 |
+
"reward": 1.7514715013094246,
|
1041 |
+
"reward_std": 3.1442014798521996,
|
1042 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.613971471786499,
|
1043 |
+
"rewards/all-MiniLM-L6-v2": -0.46250000037252903,
|
1044 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.1749999951571226,
|
1045 |
+
"rewards/length_reward": 0.42500001192092896,
|
1046 |
+
"step": 136
|
1047 |
+
},
|
1048 |
+
{
|
1049 |
+
"completion_length": 772.2000160217285,
|
1050 |
+
"epoch": 0.09402146142054164,
|
1051 |
+
"grad_norm": 0.5531837940216064,
|
1052 |
+
"kl": 0.4697265625,
|
1053 |
+
"learning_rate": 7.488520128189209e-06,
|
1054 |
+
"loss": 0.0188,
|
1055 |
+
"reward": 2.512004946358502,
|
1056 |
+
"reward_std": 2.8804666833020747,
|
1057 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6370048951357603,
|
1058 |
+
"rewards/all-MiniLM-L6-v2": -0.16249999962747097,
|
1059 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.4374999897554517,
|
1060 |
+
"rewards/length_reward": 0.6000000163912773,
|
1061 |
+
"step": 138
|
1062 |
+
},
|
1063 |
+
{
|
1064 |
+
"completion_length": 798.4750156402588,
|
1065 |
+
"epoch": 0.09538409129620166,
|
1066 |
+
"grad_norm": 0.5136257410049438,
|
1067 |
+
"kl": 0.46234130859375,
|
1068 |
+
"learning_rate": 7.182674431585703e-06,
|
1069 |
+
"loss": 0.0185,
|
1070 |
+
"reward": 2.3262645918875933,
|
1071 |
+
"reward_std": 3.08097755163908,
|
1072 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.5512645365670323,
|
1073 |
+
"rewards/all-MiniLM-L6-v2": -0.16250000055879354,
|
1074 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.4374999944120646,
|
1075 |
+
"rewards/length_reward": 0.5000000121071935,
|
1076 |
+
"step": 140
|
1077 |
+
},
|
1078 |
+
{
|
1079 |
+
"completion_length": 826.4000129699707,
|
1080 |
+
"epoch": 0.0967467211718617,
|
1081 |
+
"grad_norm": 0.5762442946434021,
|
1082 |
+
"kl": 0.52813720703125,
|
1083 |
+
"learning_rate": 6.87966554301513e-06,
|
1084 |
+
"loss": 0.0211,
|
1085 |
+
"reward": 1.824558557709679,
|
1086 |
+
"reward_std": 2.8447077772580087,
|
1087 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.5995585434138775,
|
1088 |
+
"rewards/all-MiniLM-L6-v2": -0.36249999422580004,
|
1089 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.2124999975785613,
|
1090 |
+
"rewards/length_reward": 0.3750000046566129,
|
1091 |
+
"step": 142
|
1092 |
+
},
|
1093 |
+
{
|
1094 |
+
"completion_length": 750.8875217437744,
|
1095 |
+
"epoch": 0.09810935104752172,
|
1096 |
+
"grad_norm": 0.6162233948707581,
|
1097 |
+
"kl": 0.4547119140625,
|
1098 |
+
"learning_rate": 6.579798566743314e-06,
|
1099 |
+
"loss": 0.0182,
|
1100 |
+
"reward": 2.420007437467575,
|
1101 |
+
"reward_std": 2.7739858217537403,
|
1102 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6075074281543493,
|
1103 |
+
"rewards/all-MiniLM-L6-v2": -0.19999999832361937,
|
1104 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.437499993480742,
|
1105 |
+
"rewards/length_reward": 0.575000012293458,
|
1106 |
+
"step": 144
|
1107 |
+
},
|
1108 |
+
{
|
1109 |
+
"completion_length": 734.2625026702881,
|
1110 |
+
"epoch": 0.09947198092318174,
|
1111 |
+
"grad_norm": 0.5969240069389343,
|
1112 |
+
"kl": 0.5074462890625,
|
1113 |
+
"learning_rate": 6.283375443396726e-06,
|
1114 |
+
"loss": 0.0203,
|
1115 |
+
"reward": 2.7079888563603163,
|
1116 |
+
"reward_std": 2.7715829075314105,
|
1117 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6204887935891747,
|
1118 |
+
"rewards/all-MiniLM-L6-v2": 0.11249999888241291,
|
1119 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.3999999957159162,
|
1120 |
+
"rewards/length_reward": 0.5750000076368451,
|
1121 |
+
"step": 146
|
1122 |
+
},
|
1123 |
+
{
|
1124 |
+
"completion_length": 684.1750106811523,
|
1125 |
+
"epoch": 0.10083461079884176,
|
1126 |
+
"grad_norm": 0.6124630570411682,
|
1127 |
+
"kl": 0.4541015625,
|
1128 |
+
"learning_rate": 5.990694645933866e-06,
|
1129 |
+
"loss": 0.0182,
|
1130 |
+
"reward": 2.8833600133657455,
|
1131 |
+
"reward_std": 2.8265584837645292,
|
1132 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6833599451929331,
|
1133 |
+
"rewards/all-MiniLM-L6-v2": 0.21249999944120646,
|
1134 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.437499993480742,
|
1135 |
+
"rewards/length_reward": 0.550000011920929,
|
1136 |
+
"step": 148
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"completion_length": 623.0000114440918,
|
1140 |
+
"epoch": 0.10219724067450178,
|
1141 |
+
"grad_norm": 0.6724729537963867,
|
1142 |
+
"kl": 0.4202880859375,
|
1143 |
+
"learning_rate": 5.702050879108284e-06,
|
1144 |
+
"loss": 0.0168,
|
1145 |
+
"reward": 3.6663911901414394,
|
1146 |
+
"reward_std": 1.9338009762577713,
|
1147 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.7163911033421755,
|
1148 |
+
"rewards/all-MiniLM-L6-v2": 0.4750000014901161,
|
1149 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.699999992735684,
|
1150 |
+
"rewards/length_reward": 0.7750000106170774,
|
1151 |
+
"step": 150
|
1152 |
+
},
|
1153 |
+
{
|
1154 |
+
"completion_length": 674.3875122070312,
|
1155 |
+
"epoch": 0.10355987055016182,
|
1156 |
+
"grad_norm": 0.5944858193397522,
|
1157 |
+
"kl": 0.4415283203125,
|
1158 |
+
"learning_rate": 5.417734782725896e-06,
|
1159 |
+
"loss": 0.0177,
|
1160 |
+
"reward": 3.1010947674512863,
|
1161 |
+
"reward_std": 2.580965321045369,
|
1162 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.7135947253555059,
|
1163 |
+
"rewards/all-MiniLM-L6-v2": 0.28749999962747097,
|
1164 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.5499999932944775,
|
1165 |
+
"rewards/length_reward": 0.5500000081956387,
|
1166 |
+
"step": 152
|
1167 |
+
},
|
1168 |
+
{
|
1169 |
+
"completion_length": 717.3375110626221,
|
1170 |
+
"epoch": 0.10492250042582184,
|
1171 |
+
"grad_norm": 0.6234627366065979,
|
1172 |
+
"kl": 0.489990234375,
|
1173 |
+
"learning_rate": 5.138032638995315e-06,
|
1174 |
+
"loss": 0.0196,
|
1175 |
+
"reward": 2.735639053862542,
|
1176 |
+
"reward_std": 2.6947292862460017,
|
1177 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6606389936059713,
|
1178 |
+
"rewards/all-MiniLM-L6-v2": 0.062499999068677425,
|
1179 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.5874999957159162,
|
1180 |
+
"rewards/length_reward": 0.4250000072643161,
|
1181 |
+
"step": 154
|
1182 |
+
},
|
1183 |
+
{
|
1184 |
+
"completion_length": 629.3750095367432,
|
1185 |
+
"epoch": 0.10628513030148186,
|
1186 |
+
"grad_norm": 0.6413260102272034,
|
1187 |
+
"kl": 0.4696044921875,
|
1188 |
+
"learning_rate": 4.863226084265939e-06,
|
1189 |
+
"loss": 0.0188,
|
1190 |
+
"reward": 3.1933979094028473,
|
1191 |
+
"reward_std": 2.0305717810988426,
|
1192 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.71839783154428,
|
1193 |
+
"rewards/all-MiniLM-L6-v2": 0.2875000024214387,
|
1194 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.5874999929219484,
|
1195 |
+
"rewards/length_reward": 0.6000000080093741,
|
1196 |
+
"step": 156
|
1197 |
+
},
|
1198 |
+
{
|
1199 |
+
"completion_length": 742.8625106811523,
|
1200 |
+
"epoch": 0.10764776017714188,
|
1201 |
+
"grad_norm": 0.5482673645019531,
|
1202 |
+
"kl": 0.4775390625,
|
1203 |
+
"learning_rate": 4.593591825444028e-06,
|
1204 |
+
"loss": 0.0191,
|
1205 |
+
"reward": 2.9363540150225163,
|
1206 |
+
"reward_std": 2.4036293793469667,
|
1207 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6613539699465036,
|
1208 |
+
"rewards/all-MiniLM-L6-v2": 0.1000000024214387,
|
1209 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.6249999897554517,
|
1210 |
+
"rewards/length_reward": 0.5500000109896064,
|
1211 |
+
"step": 158
|
1212 |
+
},
|
1213 |
+
{
|
1214 |
+
"completion_length": 828.2000198364258,
|
1215 |
+
"epoch": 0.10901039005280191,
|
1216 |
+
"grad_norm": 0.534371018409729,
|
1217 |
+
"kl": 0.58740234375,
|
1218 |
+
"learning_rate": 4.3294013613722944e-06,
|
1219 |
+
"loss": 0.0235,
|
1220 |
+
"reward": 2.148466292768717,
|
1221 |
+
"reward_std": 2.682615263853222,
|
1222 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6359662003815174,
|
1223 |
+
"rewards/all-MiniLM-L6-v2": -0.34999999962747097,
|
1224 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.4374999962747097,
|
1225 |
+
"rewards/length_reward": 0.42500000540167093,
|
1226 |
+
"step": 160
|
1227 |
+
},
|
1228 |
+
{
|
1229 |
+
"completion_length": 742.5875148773193,
|
1230 |
+
"epoch": 0.11037301992846194,
|
1231 |
+
"grad_norm": 0.5626158714294434,
|
1232 |
+
"kl": 0.444580078125,
|
1233 |
+
"learning_rate": 4.070920709453597e-06,
|
1234 |
+
"loss": 0.0178,
|
1235 |
+
"reward": 2.9018475273624063,
|
1236 |
+
"reward_std": 2.3305454067885876,
|
1237 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.7143475078046322,
|
1238 |
+
"rewards/all-MiniLM-L6-v2": -0.08750000037252903,
|
1239 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.6249999962747097,
|
1240 |
+
"rewards/length_reward": 0.650000006891787,
|
1241 |
+
"step": 162
|
1242 |
+
},
|
1243 |
+
{
|
1244 |
+
"completion_length": 766.9125213623047,
|
1245 |
+
"epoch": 0.11173564980412196,
|
1246 |
+
"grad_norm": 0.5314887762069702,
|
1247 |
+
"kl": 0.4736328125,
|
1248 |
+
"learning_rate": 3.818410137793947e-06,
|
1249 |
+
"loss": 0.019,
|
1250 |
+
"reward": 2.8508432680973783,
|
1251 |
+
"reward_std": 2.2408911171369255,
|
1252 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.7008432727307081,
|
1253 |
+
"rewards/all-MiniLM-L6-v2": -0.08749999944120646,
|
1254 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.5874999929219484,
|
1255 |
+
"rewards/length_reward": 0.6500000124797225,
|
1256 |
+
"step": 164
|
1257 |
+
},
|
1258 |
+
{
|
1259 |
+
"completion_length": 800.5875053405762,
|
1260 |
+
"epoch": 0.11309827967978198,
|
1261 |
+
"grad_norm": 0.6379206776618958,
|
1262 |
+
"kl": 0.4525146484375,
|
1263 |
+
"learning_rate": 3.5721239031346067e-06,
|
1264 |
+
"loss": 0.0181,
|
1265 |
+
"reward": 2.8181837666779757,
|
1266 |
+
"reward_std": 1.9853734835051,
|
1267 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.7431836733594537,
|
1268 |
+
"rewards/all-MiniLM-L6-v2": -0.07500000111758709,
|
1269 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.549999998882413,
|
1270 |
+
"rewards/length_reward": 0.6000000042840838,
|
1271 |
+
"step": 166
|
1272 |
+
},
|
1273 |
+
{
|
1274 |
+
"completion_length": 709.2625160217285,
|
1275 |
+
"epoch": 0.114460909555442,
|
1276 |
+
"grad_norm": 0.596421480178833,
|
1277 |
+
"kl": 0.461669921875,
|
1278 |
+
"learning_rate": 3.3323099948370853e-06,
|
1279 |
+
"loss": 0.0185,
|
1280 |
+
"reward": 3.579191967844963,
|
1281 |
+
"reward_std": 1.6637917342595756,
|
1282 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.7166919354349375,
|
1283 |
+
"rewards/all-MiniLM-L6-v2": 0.32499999925494194,
|
1284 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.7374999932944775,
|
1285 |
+
"rewards/length_reward": 0.8000000063329935,
|
1286 |
+
"step": 168
|
1287 |
+
},
|
1288 |
+
{
|
1289 |
+
"completion_length": 778.4750156402588,
|
1290 |
+
"epoch": 0.11582353943110203,
|
1291 |
+
"grad_norm": 0.5588167309761047,
|
1292 |
+
"kl": 0.4560546875,
|
1293 |
+
"learning_rate": 3.099209885178882e-06,
|
1294 |
+
"loss": 0.0182,
|
1295 |
+
"reward": 2.6490836143493652,
|
1296 |
+
"reward_std": 2.552674914477393,
|
1297 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.7615835480391979,
|
1298 |
+
"rewards/all-MiniLM-L6-v2": -0.18749999813735485,
|
1299 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.4749999921768904,
|
1300 |
+
"rewards/length_reward": 0.6000000108033419,
|
1301 |
+
"step": 170
|
1302 |
+
},
|
1303 |
+
{
|
1304 |
+
"completion_length": 792.4125118255615,
|
1305 |
+
"epoch": 0.11718616930676205,
|
1306 |
+
"grad_norm": 0.5151498317718506,
|
1307 |
+
"kl": 0.47119140625,
|
1308 |
+
"learning_rate": 2.8730582862113743e-06,
|
1309 |
+
"loss": 0.0188,
|
1310 |
+
"reward": 2.72108455048874,
|
1311 |
+
"reward_std": 2.322652825154364,
|
1312 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.7460845243185759,
|
1313 |
+
"rewards/all-MiniLM-L6-v2": -0.27499999944120646,
|
1314 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.6249999925494194,
|
1315 |
+
"rewards/length_reward": 0.6250000139698386,
|
1316 |
+
"step": 172
|
1317 |
+
},
|
1318 |
+
{
|
1319 |
+
"completion_length": 821.4250068664551,
|
1320 |
+
"epoch": 0.11854879918242207,
|
1321 |
+
"grad_norm": 0.5205643773078918,
|
1322 |
+
"kl": 0.52734375,
|
1323 |
+
"learning_rate": 2.6540829134246683e-06,
|
1324 |
+
"loss": 0.0211,
|
1325 |
+
"reward": 2.610885198402684,
|
1326 |
+
"reward_std": 3.1788224331103265,
|
1327 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6858852654695511,
|
1328 |
+
"rewards/all-MiniLM-L6-v2": -0.01249999925494194,
|
1329 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.3624999867752194,
|
1330 |
+
"rewards/length_reward": 0.5750000169500709,
|
1331 |
+
"step": 174
|
1332 |
+
},
|
1333 |
+
{
|
1334 |
+
"completion_length": 837.5875053405762,
|
1335 |
+
"epoch": 0.1199114290580821,
|
1336 |
+
"grad_norm": 0.5888510942459106,
|
1337 |
+
"kl": 0.466461181640625,
|
1338 |
+
"learning_rate": 2.4425042564574186e-06,
|
1339 |
+
"loss": 0.0187,
|
1340 |
+
"reward": 2.845615219324827,
|
1341 |
+
"reward_std": 2.686575308907777,
|
1342 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.708115229383111,
|
1343 |
+
"rewards/all-MiniLM-L6-v2": 0.1000000024214387,
|
1344 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.4374999897554517,
|
1345 |
+
"rewards/length_reward": 0.6000000108033419,
|
1346 |
+
"step": 176
|
1347 |
+
},
|
1348 |
+
{
|
1349 |
+
"completion_length": 891.9000205993652,
|
1350 |
+
"epoch": 0.12127405893374212,
|
1351 |
+
"grad_norm": 0.5735381841659546,
|
1352 |
+
"kl": 0.5396728515625,
|
1353 |
+
"learning_rate": 2.2385353570824308e-06,
|
1354 |
+
"loss": 0.0216,
|
1355 |
+
"reward": 2.17099030315876,
|
1356 |
+
"reward_std": 2.5423294971697032,
|
1357 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6709902733564377,
|
1358 |
+
"rewards/all-MiniLM-L6-v2": -0.2999999998137355,
|
1359 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.3249999964609742,
|
1360 |
+
"rewards/length_reward": 0.47500000707805157,
|
1361 |
+
"step": 178
|
1362 |
+
},
|
1363 |
+
{
|
1364 |
+
"completion_length": 876.9625091552734,
|
1365 |
+
"epoch": 0.12263668880940215,
|
1366 |
+
"grad_norm": 0.4231950342655182,
|
1367 |
+
"kl": 0.4525146484375,
|
1368 |
+
"learning_rate": 2.0423815946916783e-06,
|
1369 |
+
"loss": 0.0181,
|
1370 |
+
"reward": 2.40277567692101,
|
1371 |
+
"reward_std": 2.6864251531660557,
|
1372 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6652756258845329,
|
1373 |
+
"rewards/all-MiniLM-L6-v2": -0.38749999925494194,
|
1374 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.5499999932944775,
|
1375 |
+
"rewards/length_reward": 0.5750000150874257,
|
1376 |
+
"step": 180
|
1377 |
+
},
|
1378 |
+
{
|
1379 |
+
"completion_length": 771.4625129699707,
|
1380 |
+
"epoch": 0.12399931868506217,
|
1381 |
+
"grad_norm": 0.6879674196243286,
|
1382 |
+
"kl": 0.4241943359375,
|
1383 |
+
"learning_rate": 1.854240479496643e-06,
|
1384 |
+
"loss": 0.017,
|
1385 |
+
"reward": 2.696409245952964,
|
1386 |
+
"reward_std": 2.6794386385008693,
|
1387 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.7464092001318932,
|
1388 |
+
"rewards/all-MiniLM-L6-v2": -0.16249999962747097,
|
1389 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.512499999254942,
|
1390 |
+
"rewards/length_reward": 0.600000006146729,
|
1391 |
+
"step": 182
|
1392 |
+
},
|
1393 |
+
{
|
1394 |
+
"completion_length": 856.8250198364258,
|
1395 |
+
"epoch": 0.1253619485607222,
|
1396 |
+
"grad_norm": 0.5000143051147461,
|
1397 |
+
"kl": 0.489013671875,
|
1398 |
+
"learning_rate": 1.6743014536522872e-06,
|
1399 |
+
"loss": 0.0196,
|
1400 |
+
"reward": 2.656417434802279,
|
1401 |
+
"reward_std": 2.805582005530596,
|
1402 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6689173814374954,
|
1403 |
+
"rewards/all-MiniLM-L6-v2": 0.10000000055879354,
|
1404 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.2874999940395355,
|
1405 |
+
"rewards/length_reward": 0.6000000108033419,
|
1406 |
+
"step": 184
|
1407 |
+
},
|
1408 |
+
{
|
1409 |
+
"completion_length": 966.1875114440918,
|
1410 |
+
"epoch": 0.1267245784363822,
|
1411 |
+
"grad_norm": 0.5162502527236938,
|
1412 |
+
"kl": 0.565032958984375,
|
1413 |
+
"learning_rate": 1.5027457005048573e-06,
|
1414 |
+
"loss": 0.0226,
|
1415 |
+
"reward": 2.036801053909585,
|
1416 |
+
"reward_std": 2.7416782565414906,
|
1417 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6243010433390737,
|
1418 |
+
"rewards/all-MiniLM-L6-v2": -0.16250000149011612,
|
1419 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.1749999970197678,
|
1420 |
+
"rewards/length_reward": 0.4000000013038516,
|
1421 |
+
"step": 186
|
1422 |
+
},
|
1423 |
+
{
|
1424 |
+
"completion_length": 861.5000190734863,
|
1425 |
+
"epoch": 0.12808720831204223,
|
1426 |
+
"grad_norm": 0.5157842040061951,
|
1427 |
+
"kl": 0.493896484375,
|
1428 |
+
"learning_rate": 1.339745962155613e-06,
|
1429 |
+
"loss": 0.0197,
|
1430 |
+
"reward": 2.1817345349118114,
|
1431 |
+
"reward_std": 2.4753956105560064,
|
1432 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6442344710230827,
|
1433 |
+
"rewards/all-MiniLM-L6-v2": -0.49999999813735485,
|
1434 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.5124999918043613,
|
1435 |
+
"rewards/length_reward": 0.525000006891787,
|
1436 |
+
"step": 188
|
1437 |
+
},
|
1438 |
+
{
|
1439 |
+
"completion_length": 839.6875190734863,
|
1440 |
+
"epoch": 0.12944983818770225,
|
1441 |
+
"grad_norm": 0.4954194128513336,
|
1442 |
+
"kl": 0.483642578125,
|
1443 |
+
"learning_rate": 1.1854663655241804e-06,
|
1444 |
+
"loss": 0.0193,
|
1445 |
+
"reward": 2.925493508577347,
|
1446 |
+
"reward_std": 2.9417885206639767,
|
1447 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.7129934653639793,
|
1448 |
+
"rewards/all-MiniLM-L6-v2": 0.06250000186264515,
|
1449 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.4749999903142452,
|
1450 |
+
"rewards/length_reward": 0.6750000109896064,
|
1451 |
+
"step": 190
|
1452 |
+
},
|
1453 |
+
{
|
1454 |
+
"completion_length": 824.5375061035156,
|
1455 |
+
"epoch": 0.1308124680633623,
|
1456 |
+
"grad_norm": 0.4791363477706909,
|
1457 |
+
"kl": 0.4300537109375,
|
1458 |
+
"learning_rate": 1.0400622570866426e-06,
|
1459 |
+
"loss": 0.0172,
|
1460 |
+
"reward": 2.805993139743805,
|
1461 |
+
"reward_std": 2.586992080323398,
|
1462 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.7059930665418506,
|
1463 |
+
"rewards/all-MiniLM-L6-v2": -0.050000001676380634,
|
1464 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.5499999932944775,
|
1465 |
+
"rewards/length_reward": 0.6000000108033419,
|
1466 |
+
"step": 192
|
1467 |
+
},
|
1468 |
+
{
|
1469 |
+
"completion_length": 923.1625137329102,
|
1470 |
+
"epoch": 0.13217509793902232,
|
1471 |
+
"grad_norm": 0.40569427609443665,
|
1472 |
+
"kl": 0.61822509765625,
|
1473 |
+
"learning_rate": 9.036800464548157e-07,
|
1474 |
+
"loss": 0.0247,
|
1475 |
+
"reward": 2.090137917548418,
|
1476 |
+
"reward_std": 3.2905192878097296,
|
1477 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6651378944516182,
|
1478 |
+
"rewards/all-MiniLM-L6-v2": -0.23750000447034836,
|
1479 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.2124999891966581,
|
1480 |
+
"rewards/length_reward": 0.45000001043081284,
|
1481 |
+
"step": 194
|
1482 |
+
},
|
1483 |
+
{
|
1484 |
+
"completion_length": 860.8375129699707,
|
1485 |
+
"epoch": 0.13353772781468234,
|
1486 |
+
"grad_norm": 0.49536529183387756,
|
1487 |
+
"kl": 0.450927734375,
|
1488 |
+
"learning_rate": 7.764570589541876e-07,
|
1489 |
+
"loss": 0.018,
|
1490 |
+
"reward": 2.6283551678061485,
|
1491 |
+
"reward_std": 2.2464691884815693,
|
1492 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.7033550683408976,
|
1493 |
+
"rewards/all-MiniLM-L6-v2": -0.23749999701976776,
|
1494 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.5874999919906259,
|
1495 |
+
"rewards/length_reward": 0.5750000067055225,
|
1496 |
+
"step": 196
|
1497 |
+
},
|
1498 |
+
{
|
1499 |
+
"completion_length": 886.8375091552734,
|
1500 |
+
"epoch": 0.13490035769034237,
|
1501 |
+
"grad_norm": 0.5045952200889587,
|
1502 |
+
"kl": 0.5023193359375,
|
1503 |
+
"learning_rate": 6.585213973489335e-07,
|
1504 |
+
"loss": 0.0201,
|
1505 |
+
"reward": 2.5980349611490965,
|
1506 |
+
"reward_std": 2.6176577494479716,
|
1507 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6730349091812968,
|
1508 |
+
"rewards/all-MiniLM-L6-v2": -0.125,
|
1509 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.474999994970858,
|
1510 |
+
"rewards/length_reward": 0.5750000094994903,
|
1511 |
+
"step": 198
|
1512 |
+
},
|
1513 |
+
{
|
1514 |
+
"completion_length": 821.5750122070312,
|
1515 |
+
"epoch": 0.13626298756600239,
|
1516 |
+
"grad_norm": 0.5383718609809875,
|
1517 |
+
"kl": 0.44384765625,
|
1518 |
+
"learning_rate": 5.499918128533155e-07,
|
1519 |
+
"loss": 0.0178,
|
1520 |
+
"reward": 2.671635969541967,
|
1521 |
+
"reward_std": 2.3409718545153737,
|
1522 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.7591358739882708,
|
1523 |
+
"rewards/all-MiniLM-L6-v2": -0.3124999990686774,
|
1524 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.6249999972060323,
|
1525 |
+
"rewards/length_reward": 0.600000012665987,
|
1526 |
+
"step": 200
|
1527 |
+
},
|
1528 |
+
{
|
1529 |
+
"epoch": 0.13626298756600239,
|
1530 |
+
"eval_completion_length": 901.0770969390869,
|
1531 |
+
"eval_kl": 0.51776123046875,
|
1532 |
+
"eval_loss": 0.020734939724206924,
|
1533 |
+
"eval_reward": 2.2421040004119277,
|
1534 |
+
"eval_reward_std": 3.041678664914798,
|
1535 |
+
"eval_rewards/AnswerChecker_LenCheck_Reward": 0.6764789510052651,
|
1536 |
+
"eval_rewards/all-MiniLM-L6-v2": -0.21718749997671694,
|
1537 |
+
"eval_rewards/format_reward_beginEndSolutionFormat": 1.2921874948078766,
|
1538 |
+
"eval_rewards/length_reward": 0.4906250089406967,
|
1539 |
+
"eval_runtime": 1491.0997,
|
1540 |
+
"eval_samples_per_second": 0.086,
|
1541 |
+
"eval_steps_per_second": 0.017,
|
1542 |
+
"step": 200
|
1543 |
+
},
|
1544 |
+
{
|
1545 |
+
"completion_length": 868.400016784668,
|
1546 |
+
"epoch": 0.1376256174416624,
|
1547 |
+
"grad_norm": 0.5225978493690491,
|
1548 |
+
"kl": 0.470703125,
|
1549 |
+
"learning_rate": 4.509775855592613e-07,
|
1550 |
+
"loss": 0.0188,
|
1551 |
+
"reward": 2.6535421311855316,
|
1552 |
+
"reward_std": 2.792340838816017,
|
1553 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6660420242697,
|
1554 |
+
"rewards/all-MiniLM-L6-v2": 0.08750000316649675,
|
1555 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.3249999936670065,
|
1556 |
+
"rewards/length_reward": 0.5750000094994903,
|
1557 |
+
"step": 202
|
1558 |
+
},
|
1559 |
+
{
|
1560 |
+
"completion_length": 866.7875213623047,
|
1561 |
+
"epoch": 0.13898824731732243,
|
1562 |
+
"grad_norm": 0.4848329722881317,
|
1563 |
+
"kl": 0.485107421875,
|
1564 |
+
"learning_rate": 3.615784144005796e-07,
|
1565 |
+
"loss": 0.0194,
|
1566 |
+
"reward": 2.717348374426365,
|
1567 |
+
"reward_std": 3.1343387353699654,
|
1568 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.7048483230173588,
|
1569 |
+
"rewards/all-MiniLM-L6-v2": 0.06250000186264515,
|
1570 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.3999999919906259,
|
1571 |
+
"rewards/length_reward": 0.550000011920929,
|
1572 |
+
"step": 204
|
1573 |
+
},
|
1574 |
+
{
|
1575 |
+
"completion_length": 899.8250122070312,
|
1576 |
+
"epoch": 0.14035087719298245,
|
1577 |
+
"grad_norm": 0.7146245837211609,
|
1578 |
+
"kl": 1.0164794921875,
|
1579 |
+
"learning_rate": 2.818843167645835e-07,
|
1580 |
+
"loss": 0.0407,
|
1581 |
+
"reward": 2.0691821854561567,
|
1582 |
+
"reward_std": 3.262540274299681,
|
1583 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6441821809858084,
|
1584 |
+
"rewards/all-MiniLM-L6-v2": -0.23750000074505806,
|
1585 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.2124999957159162,
|
1586 |
+
"rewards/length_reward": 0.4500000076368451,
|
1587 |
+
"step": 206
|
1588 |
+
},
|
1589 |
+
{
|
1590 |
+
"completion_length": 891.0625190734863,
|
1591 |
+
"epoch": 0.14171350706864247,
|
1592 |
+
"grad_norm": 0.4813491702079773,
|
1593 |
+
"kl": 0.4830322265625,
|
1594 |
+
"learning_rate": 2.119755378522137e-07,
|
1595 |
+
"loss": 0.0193,
|
1596 |
+
"reward": 2.4804067488294095,
|
1597 |
+
"reward_std": 2.613793831784278,
|
1598 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.680406715720892,
|
1599 |
+
"rewards/all-MiniLM-L6-v2": -0.04999999608844519,
|
1600 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.325000001117587,
|
1601 |
+
"rewards/length_reward": 0.5250000078231096,
|
1602 |
+
"step": 208
|
1603 |
+
},
|
1604 |
+
{
|
1605 |
+
"completion_length": 837.337516784668,
|
1606 |
+
"epoch": 0.1430761369443025,
|
1607 |
+
"grad_norm": 0.4959147870540619,
|
1608 |
+
"kl": 0.4730224609375,
|
1609 |
+
"learning_rate": 1.519224698779198e-07,
|
1610 |
+
"loss": 0.0189,
|
1611 |
+
"reward": 2.9152769446372986,
|
1612 |
+
"reward_std": 2.3198010358028114,
|
1613 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.7527768295258284,
|
1614 |
+
"rewards/all-MiniLM-L6-v2": 1.862645149230957e-09,
|
1615 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.5874999957159162,
|
1616 |
+
"rewards/length_reward": 0.5750000039115548,
|
1617 |
+
"step": 210
|
1618 |
+
},
|
1619 |
+
{
|
1620 |
+
"completion_length": 871.5125160217285,
|
1621 |
+
"epoch": 0.14443876681996254,
|
1622 |
+
"grad_norm": 0.9553112387657166,
|
1623 |
+
"kl": 0.5531005859375,
|
1624 |
+
"learning_rate": 1.0178558119067316e-07,
|
1625 |
+
"loss": 0.0221,
|
1626 |
+
"reward": 2.6484466195106506,
|
1627 |
+
"reward_std": 2.807733765337616,
|
1628 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6984465261921287,
|
1629 |
+
"rewards/all-MiniLM-L6-v2": 0.08750000223517418,
|
1630 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.2874999893829226,
|
1631 |
+
"rewards/length_reward": 0.5750000076368451,
|
1632 |
+
"step": 212
|
1633 |
+
},
|
1634 |
+
{
|
1635 |
+
"completion_length": 909.4750137329102,
|
1636 |
+
"epoch": 0.14580139669562256,
|
1637 |
+
"grad_norm": 0.5723004937171936,
|
1638 |
+
"kl": 0.57098388671875,
|
1639 |
+
"learning_rate": 6.161535538745877e-08,
|
1640 |
+
"loss": 0.0229,
|
1641 |
+
"reward": 1.5668016755953431,
|
1642 |
+
"reward_std": 2.593209580751136,
|
1643 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6418016445823014,
|
1644 |
+
"rewards/all-MiniLM-L6-v2": -0.5000000027939677,
|
1645 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.0249999966472387,
|
1646 |
+
"rewards/length_reward": 0.40000000316649675,
|
1647 |
+
"step": 214
|
1648 |
+
},
|
1649 |
+
{
|
1650 |
+
"completion_length": 968.3375205993652,
|
1651 |
+
"epoch": 0.14716402657128258,
|
1652 |
+
"grad_norm": 0.4992906153202057,
|
1653 |
+
"kl": 0.6209716796875,
|
1654 |
+
"learning_rate": 3.1452240480577265e-08,
|
1655 |
+
"loss": 0.0248,
|
1656 |
+
"reward": 1.5952948506455868,
|
1657 |
+
"reward_std": 3.052502178354189,
|
1658 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6452948525547981,
|
1659 |
+
"rewards/all-MiniLM-L6-v2": -0.462499993853271,
|
1660 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.062499993480742,
|
1661 |
+
"rewards/length_reward": 0.350000006146729,
|
1662 |
+
"step": 216
|
1663 |
+
},
|
1664 |
+
{
|
1665 |
+
"completion_length": 888.4625244140625,
|
1666 |
+
"epoch": 0.1485266564469426,
|
1667 |
+
"grad_norm": 0.5244458913803101,
|
1668 |
+
"kl": 0.5447998046875,
|
1669 |
+
"learning_rate": 1.1326608169920373e-08,
|
1670 |
+
"loss": 0.0218,
|
1671 |
+
"reward": 2.0069867819547653,
|
1672 |
+
"reward_std": 2.44455174729228,
|
1673 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6694867238402367,
|
1674 |
+
"rewards/all-MiniLM-L6-v2": -0.4124999986961484,
|
1675 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.2499999990686774,
|
1676 |
+
"rewards/length_reward": 0.5000000046566129,
|
1677 |
+
"step": 218
|
1678 |
+
},
|
1679 |
+
{
|
1680 |
+
"completion_length": 940.7250213623047,
|
1681 |
+
"epoch": 0.14988928632260262,
|
1682 |
+
"grad_norm": 0.45825526118278503,
|
1683 |
+
"kl": 0.569427490234375,
|
1684 |
+
"learning_rate": 1.2587232612493172e-09,
|
1685 |
+
"loss": 0.0228,
|
1686 |
+
"reward": 2.0391996294492856,
|
1687 |
+
"reward_std": 3.5446557994000614,
|
1688 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.6266996059566736,
|
1689 |
+
"rewards/all-MiniLM-L6-v2": -0.04999999608844519,
|
1690 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.0624999953433871,
|
1691 |
+
"rewards/length_reward": 0.40000000689178705,
|
1692 |
+
"step": 220
|
1693 |
+
},
|
1694 |
+
{
|
1695 |
+
"completion_length": 826.150016784668,
|
1696 |
+
"epoch": 0.15057060126043265,
|
1697 |
+
"kl": 0.503173828125,
|
1698 |
+
"reward": 2.8795320093631744,
|
1699 |
+
"reward_std": 2.7599759995937347,
|
1700 |
+
"rewards/AnswerChecker_LenCheck_Reward": 0.7045319639146328,
|
1701 |
+
"rewards/all-MiniLM-L6-v2": -0.04999999701976776,
|
1702 |
+
"rewards/format_reward_beginEndSolutionFormat": 1.6249999925494194,
|
1703 |
+
"rewards/length_reward": 0.600000012665987,
|
1704 |
+
"step": 221,
|
1705 |
+
"total_flos": 0.0,
|
1706 |
+
"train_loss": 0.014638028192195337,
|
1707 |
+
"train_runtime": 22832.117,
|
1708 |
+
"train_samples_per_second": 0.077,
|
1709 |
+
"train_steps_per_second": 0.01
|
1710 |
+
}
|
1711 |
+
],
|
1712 |
+
"logging_steps": 2,
|
1713 |
+
"max_steps": 221,
|
1714 |
+
"num_input_tokens_seen": 0,
|
1715 |
+
"num_train_epochs": 1,
|
1716 |
+
"save_steps": 30,
|
1717 |
+
"stateful_callbacks": {
|
1718 |
+
"TrainerControl": {
|
1719 |
+
"args": {
|
1720 |
+
"should_epoch_stop": false,
|
1721 |
+
"should_evaluate": false,
|
1722 |
+
"should_log": false,
|
1723 |
+
"should_save": false,
|
1724 |
+
"should_training_stop": false
|
1725 |
+
},
|
1726 |
+
"attributes": {}
|
1727 |
+
}
|
1728 |
+
},
|
1729 |
+
"total_flos": 0.0,
|
1730 |
+
"train_batch_size": 5,
|
1731 |
+
"trial_name": null,
|
1732 |
+
"trial_params": null
|
1733 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f5f63d3e5d81f6c418113f92a3e8871ea668566937438b2bd6902a667d61bce3
|
3 |
+
size 7800
|