evgmaslov commited on
Commit
3a872c0
·
verified ·
1 Parent(s): 96eca6f

Training in progress, step 100, checkpoint

Browse files
last-checkpoint/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen2.5-Coder-0.5B-Instruct
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.13.0
last-checkpoint/adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen2.5-Coder-0.5B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.1,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "v_proj",
24
+ "q_proj"
25
+ ],
26
+ "task_type": "CAUSAL_LM",
27
+ "use_dora": false,
28
+ "use_rslora": false
29
+ }
last-checkpoint/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68c32afcebac09a4eb98ed0fda7d9217f0a424563d8feb9458c4ec8e10f06585
3
+ size 17314248
last-checkpoint/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
last-checkpoint/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b1ce145f66f69c556e27883c7faae333c91225cd8ba5cf534b2ab252b05f3ec
3
+ size 34683834
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9bdca0dbbc3fd8f78a3fa278ecfc19085437efb9de438af979e30cb331e041a
3
+ size 14244
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cacd8934f9006bd3df23a6aa51009a8101dbc1475b580d25c459de1b4f6c24a
3
+ size 1064
last-checkpoint/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
last-checkpoint/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5eee858c5123a4279c3e1f7b81247343f356ac767940b2692a928ad929543214
3
+ size 11422063
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|im_end|>",
201
+ "errors": "replace",
202
+ "extra_special_tokens": {},
203
+ "model_max_length": 32768,
204
+ "pad_token": "<|endoftext|>",
205
+ "padding_side": "left",
206
+ "split_special_tokens": false,
207
+ "tokenizer_class": "Qwen2Tokenizer",
208
+ "unk_token": null
209
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,1733 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.08057206163762715,
5
+ "eval_steps": 500,
6
+ "global_step": 100,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "completion_length": 195.142578125,
13
+ "epoch": 0.0008057206163762715,
14
+ "grad_norm": 0.0,
15
+ "kl": 0.0,
16
+ "learning_rate": 9.99194198227236e-07,
17
+ "loss": 0.0,
18
+ "reward": 0.0,
19
+ "reward_std": 0.0,
20
+ "rewards/answer_format_reward": 0.0,
21
+ "rewards/common_format_reward": 0.0,
22
+ "rewards/doors_consistency_reward": 0.0,
23
+ "rewards/geometry_consistency_reward": 0.0,
24
+ "rewards/prompt_consistency_reward": 0.0,
25
+ "rewards/walls_consistency_reward": 0.0,
26
+ "step": 1
27
+ },
28
+ {
29
+ "completion_length": 204.81640625,
30
+ "epoch": 0.001611441232752543,
31
+ "grad_norm": 0.0,
32
+ "kl": 0.0,
33
+ "learning_rate": 9.983883964544722e-07,
34
+ "loss": 0.0,
35
+ "reward": 0.0,
36
+ "reward_std": 0.0,
37
+ "rewards/answer_format_reward": 0.0,
38
+ "rewards/common_format_reward": 0.0,
39
+ "rewards/doors_consistency_reward": 0.0,
40
+ "rewards/geometry_consistency_reward": 0.0,
41
+ "rewards/prompt_consistency_reward": 0.0,
42
+ "rewards/walls_consistency_reward": 0.0,
43
+ "step": 2
44
+ },
45
+ {
46
+ "completion_length": 207.009765625,
47
+ "epoch": 0.0024171618491288147,
48
+ "grad_norm": 0.0,
49
+ "kl": 0.0,
50
+ "learning_rate": 9.975825946817082e-07,
51
+ "loss": 0.0,
52
+ "reward": 0.0,
53
+ "reward_std": 0.0,
54
+ "rewards/answer_format_reward": 0.0,
55
+ "rewards/common_format_reward": 0.0,
56
+ "rewards/doors_consistency_reward": 0.0,
57
+ "rewards/geometry_consistency_reward": 0.0,
58
+ "rewards/prompt_consistency_reward": 0.0,
59
+ "rewards/walls_consistency_reward": 0.0,
60
+ "step": 3
61
+ },
62
+ {
63
+ "completion_length": 210.265625,
64
+ "epoch": 0.003222882465505086,
65
+ "grad_norm": 0.0,
66
+ "kl": 0.0,
67
+ "learning_rate": 9.967767929089443e-07,
68
+ "loss": 0.0,
69
+ "reward": 0.0,
70
+ "reward_std": 0.0,
71
+ "rewards/answer_format_reward": 0.0,
72
+ "rewards/common_format_reward": 0.0,
73
+ "rewards/doors_consistency_reward": 0.0,
74
+ "rewards/geometry_consistency_reward": 0.0,
75
+ "rewards/prompt_consistency_reward": 0.0,
76
+ "rewards/walls_consistency_reward": 0.0,
77
+ "step": 4
78
+ },
79
+ {
80
+ "completion_length": 205.4375,
81
+ "epoch": 0.004028603081881358,
82
+ "grad_norm": 0.0,
83
+ "kl": 0.0,
84
+ "learning_rate": 9.959709911361804e-07,
85
+ "loss": 0.0,
86
+ "reward": 0.0,
87
+ "reward_std": 0.0,
88
+ "rewards/answer_format_reward": 0.0,
89
+ "rewards/common_format_reward": 0.0,
90
+ "rewards/doors_consistency_reward": 0.0,
91
+ "rewards/geometry_consistency_reward": 0.0,
92
+ "rewards/prompt_consistency_reward": 0.0,
93
+ "rewards/walls_consistency_reward": 0.0,
94
+ "step": 5
95
+ },
96
+ {
97
+ "completion_length": 207.291015625,
98
+ "epoch": 0.004834323698257629,
99
+ "grad_norm": 0.0,
100
+ "kl": 0.0,
101
+ "learning_rate": 9.951651893634166e-07,
102
+ "loss": 0.0,
103
+ "reward": 0.0,
104
+ "reward_std": 0.0,
105
+ "rewards/answer_format_reward": 0.0,
106
+ "rewards/common_format_reward": 0.0,
107
+ "rewards/doors_consistency_reward": 0.0,
108
+ "rewards/geometry_consistency_reward": 0.0,
109
+ "rewards/prompt_consistency_reward": 0.0,
110
+ "rewards/walls_consistency_reward": 0.0,
111
+ "step": 6
112
+ },
113
+ {
114
+ "completion_length": 204.716796875,
115
+ "epoch": 0.005640044314633901,
116
+ "grad_norm": 0.0,
117
+ "kl": 0.0,
118
+ "learning_rate": 9.943593875906527e-07,
119
+ "loss": 0.0,
120
+ "reward": 0.0,
121
+ "reward_std": 0.0,
122
+ "rewards/answer_format_reward": 0.0,
123
+ "rewards/common_format_reward": 0.0,
124
+ "rewards/doors_consistency_reward": 0.0,
125
+ "rewards/geometry_consistency_reward": 0.0,
126
+ "rewards/prompt_consistency_reward": 0.0,
127
+ "rewards/walls_consistency_reward": 0.0,
128
+ "step": 7
129
+ },
130
+ {
131
+ "completion_length": 198.2890625,
132
+ "epoch": 0.006445764931010172,
133
+ "grad_norm": 0.0,
134
+ "kl": 0.0,
135
+ "learning_rate": 9.935535858178886e-07,
136
+ "loss": 0.0,
137
+ "reward": 0.0,
138
+ "reward_std": 0.0,
139
+ "rewards/answer_format_reward": 0.0,
140
+ "rewards/common_format_reward": 0.0,
141
+ "rewards/doors_consistency_reward": 0.0,
142
+ "rewards/geometry_consistency_reward": 0.0,
143
+ "rewards/prompt_consistency_reward": 0.0,
144
+ "rewards/walls_consistency_reward": 0.0,
145
+ "step": 8
146
+ },
147
+ {
148
+ "completion_length": 205.642578125,
149
+ "epoch": 0.007251485547386444,
150
+ "grad_norm": 0.0,
151
+ "kl": 0.0,
152
+ "learning_rate": 9.927477840451248e-07,
153
+ "loss": 0.0,
154
+ "reward": 0.0,
155
+ "reward_std": 0.0,
156
+ "rewards/answer_format_reward": 0.0,
157
+ "rewards/common_format_reward": 0.0,
158
+ "rewards/doors_consistency_reward": 0.0,
159
+ "rewards/geometry_consistency_reward": 0.0,
160
+ "rewards/prompt_consistency_reward": 0.0,
161
+ "rewards/walls_consistency_reward": 0.0,
162
+ "step": 9
163
+ },
164
+ {
165
+ "completion_length": 204.33984375,
166
+ "epoch": 0.008057206163762716,
167
+ "grad_norm": 0.0,
168
+ "kl": 0.0,
169
+ "learning_rate": 9.91941982272361e-07,
170
+ "loss": 0.0,
171
+ "reward": 0.0,
172
+ "reward_std": 0.0,
173
+ "rewards/answer_format_reward": 0.0,
174
+ "rewards/common_format_reward": 0.0,
175
+ "rewards/doors_consistency_reward": 0.0,
176
+ "rewards/geometry_consistency_reward": 0.0,
177
+ "rewards/prompt_consistency_reward": 0.0,
178
+ "rewards/walls_consistency_reward": 0.0,
179
+ "step": 10
180
+ },
181
+ {
182
+ "completion_length": 199.70703125,
183
+ "epoch": 0.008862926780138987,
184
+ "grad_norm": 0.0,
185
+ "kl": 0.0,
186
+ "learning_rate": 9.91136180499597e-07,
187
+ "loss": 0.0,
188
+ "reward": 0.0,
189
+ "reward_std": 0.0,
190
+ "rewards/answer_format_reward": 0.0,
191
+ "rewards/common_format_reward": 0.0,
192
+ "rewards/doors_consistency_reward": 0.0,
193
+ "rewards/geometry_consistency_reward": 0.0,
194
+ "rewards/prompt_consistency_reward": 0.0,
195
+ "rewards/walls_consistency_reward": 0.0,
196
+ "step": 11
197
+ },
198
+ {
199
+ "completion_length": 200.955078125,
200
+ "epoch": 0.009668647396515259,
201
+ "grad_norm": 0.0,
202
+ "kl": 0.0,
203
+ "learning_rate": 9.903303787268332e-07,
204
+ "loss": 0.0,
205
+ "reward": 0.0,
206
+ "reward_std": 0.0,
207
+ "rewards/answer_format_reward": 0.0,
208
+ "rewards/common_format_reward": 0.0,
209
+ "rewards/doors_consistency_reward": 0.0,
210
+ "rewards/geometry_consistency_reward": 0.0,
211
+ "rewards/prompt_consistency_reward": 0.0,
212
+ "rewards/walls_consistency_reward": 0.0,
213
+ "step": 12
214
+ },
215
+ {
216
+ "completion_length": 208.11328125,
217
+ "epoch": 0.01047436801289153,
218
+ "grad_norm": 0.0,
219
+ "kl": 0.0,
220
+ "learning_rate": 9.895245769540691e-07,
221
+ "loss": 0.0,
222
+ "reward": 0.0,
223
+ "reward_std": 0.0,
224
+ "rewards/answer_format_reward": 0.0,
225
+ "rewards/common_format_reward": 0.0,
226
+ "rewards/doors_consistency_reward": 0.0,
227
+ "rewards/geometry_consistency_reward": 0.0,
228
+ "rewards/prompt_consistency_reward": 0.0,
229
+ "rewards/walls_consistency_reward": 0.0,
230
+ "step": 13
231
+ },
232
+ {
233
+ "completion_length": 202.32421875,
234
+ "epoch": 0.011280088629267802,
235
+ "grad_norm": 0.0,
236
+ "kl": 0.0,
237
+ "learning_rate": 9.887187751813053e-07,
238
+ "loss": 0.0,
239
+ "reward": 0.0,
240
+ "reward_std": 0.0,
241
+ "rewards/answer_format_reward": 0.0,
242
+ "rewards/common_format_reward": 0.0,
243
+ "rewards/doors_consistency_reward": 0.0,
244
+ "rewards/geometry_consistency_reward": 0.0,
245
+ "rewards/prompt_consistency_reward": 0.0,
246
+ "rewards/walls_consistency_reward": 0.0,
247
+ "step": 14
248
+ },
249
+ {
250
+ "completion_length": 204.068359375,
251
+ "epoch": 0.012085809245644072,
252
+ "grad_norm": 0.0,
253
+ "kl": 0.0,
254
+ "learning_rate": 9.879129734085414e-07,
255
+ "loss": 0.0,
256
+ "reward": 0.0,
257
+ "reward_std": 0.0,
258
+ "rewards/answer_format_reward": 0.0,
259
+ "rewards/common_format_reward": 0.0,
260
+ "rewards/doors_consistency_reward": 0.0,
261
+ "rewards/geometry_consistency_reward": 0.0,
262
+ "rewards/prompt_consistency_reward": 0.0,
263
+ "rewards/walls_consistency_reward": 0.0,
264
+ "step": 15
265
+ },
266
+ {
267
+ "completion_length": 206.64453125,
268
+ "epoch": 0.012891529862020345,
269
+ "grad_norm": 0.0,
270
+ "kl": 0.0,
271
+ "learning_rate": 9.871071716357775e-07,
272
+ "loss": 0.0,
273
+ "reward": 0.0,
274
+ "reward_std": 0.0,
275
+ "rewards/answer_format_reward": 0.0,
276
+ "rewards/common_format_reward": 0.0,
277
+ "rewards/doors_consistency_reward": 0.0,
278
+ "rewards/geometry_consistency_reward": 0.0,
279
+ "rewards/prompt_consistency_reward": 0.0,
280
+ "rewards/walls_consistency_reward": 0.0,
281
+ "step": 16
282
+ },
283
+ {
284
+ "completion_length": 207.431640625,
285
+ "epoch": 0.013697250478396617,
286
+ "grad_norm": 0.0,
287
+ "kl": 0.0,
288
+ "learning_rate": 9.863013698630137e-07,
289
+ "loss": 0.0,
290
+ "reward": 0.0,
291
+ "reward_std": 0.0,
292
+ "rewards/answer_format_reward": 0.0,
293
+ "rewards/common_format_reward": 0.0,
294
+ "rewards/doors_consistency_reward": 0.0,
295
+ "rewards/geometry_consistency_reward": 0.0,
296
+ "rewards/prompt_consistency_reward": 0.0,
297
+ "rewards/walls_consistency_reward": 0.0,
298
+ "step": 17
299
+ },
300
+ {
301
+ "completion_length": 206.13671875,
302
+ "epoch": 0.014502971094772887,
303
+ "grad_norm": 0.0,
304
+ "kl": 0.0,
305
+ "learning_rate": 9.854955680902498e-07,
306
+ "loss": 0.0,
307
+ "reward": 0.0,
308
+ "reward_std": 0.0,
309
+ "rewards/answer_format_reward": 0.0,
310
+ "rewards/common_format_reward": 0.0,
311
+ "rewards/doors_consistency_reward": 0.0,
312
+ "rewards/geometry_consistency_reward": 0.0,
313
+ "rewards/prompt_consistency_reward": 0.0,
314
+ "rewards/walls_consistency_reward": 0.0,
315
+ "step": 18
316
+ },
317
+ {
318
+ "completion_length": 208.638671875,
319
+ "epoch": 0.01530869171114916,
320
+ "grad_norm": 0.0,
321
+ "kl": 0.0,
322
+ "learning_rate": 9.84689766317486e-07,
323
+ "loss": 0.0,
324
+ "reward": 0.0,
325
+ "reward_std": 0.0,
326
+ "rewards/answer_format_reward": 0.0,
327
+ "rewards/common_format_reward": 0.0,
328
+ "rewards/doors_consistency_reward": 0.0,
329
+ "rewards/geometry_consistency_reward": 0.0,
330
+ "rewards/prompt_consistency_reward": 0.0,
331
+ "rewards/walls_consistency_reward": 0.0,
332
+ "step": 19
333
+ },
334
+ {
335
+ "completion_length": 199.166015625,
336
+ "epoch": 0.016114412327525432,
337
+ "grad_norm": 0.0,
338
+ "kl": 0.0,
339
+ "learning_rate": 9.83883964544722e-07,
340
+ "loss": 0.0,
341
+ "reward": 0.0,
342
+ "reward_std": 0.0,
343
+ "rewards/answer_format_reward": 0.0,
344
+ "rewards/common_format_reward": 0.0,
345
+ "rewards/doors_consistency_reward": 0.0,
346
+ "rewards/geometry_consistency_reward": 0.0,
347
+ "rewards/prompt_consistency_reward": 0.0,
348
+ "rewards/walls_consistency_reward": 0.0,
349
+ "step": 20
350
+ },
351
+ {
352
+ "completion_length": 205.33984375,
353
+ "epoch": 0.0169201329439017,
354
+ "grad_norm": 0.0,
355
+ "kl": 0.0,
356
+ "learning_rate": 9.83078162771958e-07,
357
+ "loss": 0.0,
358
+ "reward": 0.0,
359
+ "reward_std": 0.0,
360
+ "rewards/answer_format_reward": 0.0,
361
+ "rewards/common_format_reward": 0.0,
362
+ "rewards/doors_consistency_reward": 0.0,
363
+ "rewards/geometry_consistency_reward": 0.0,
364
+ "rewards/prompt_consistency_reward": 0.0,
365
+ "rewards/walls_consistency_reward": 0.0,
366
+ "step": 21
367
+ },
368
+ {
369
+ "completion_length": 206.173828125,
370
+ "epoch": 0.017725853560277973,
371
+ "grad_norm": 0.0,
372
+ "kl": 0.0,
373
+ "learning_rate": 9.822723609991942e-07,
374
+ "loss": 0.0,
375
+ "reward": 0.0,
376
+ "reward_std": 0.0,
377
+ "rewards/answer_format_reward": 0.0,
378
+ "rewards/common_format_reward": 0.0,
379
+ "rewards/doors_consistency_reward": 0.0,
380
+ "rewards/geometry_consistency_reward": 0.0,
381
+ "rewards/prompt_consistency_reward": 0.0,
382
+ "rewards/walls_consistency_reward": 0.0,
383
+ "step": 22
384
+ },
385
+ {
386
+ "completion_length": 204.033203125,
387
+ "epoch": 0.018531574176654245,
388
+ "grad_norm": 0.0,
389
+ "kl": 0.0,
390
+ "learning_rate": 9.814665592264303e-07,
391
+ "loss": 0.0,
392
+ "reward": 0.0,
393
+ "reward_std": 0.0,
394
+ "rewards/answer_format_reward": 0.0,
395
+ "rewards/common_format_reward": 0.0,
396
+ "rewards/doors_consistency_reward": 0.0,
397
+ "rewards/geometry_consistency_reward": 0.0,
398
+ "rewards/prompt_consistency_reward": 0.0,
399
+ "rewards/walls_consistency_reward": 0.0,
400
+ "step": 23
401
+ },
402
+ {
403
+ "completion_length": 202.673828125,
404
+ "epoch": 0.019337294793030518,
405
+ "grad_norm": 0.0,
406
+ "kl": 0.0,
407
+ "learning_rate": 9.806607574536664e-07,
408
+ "loss": 0.0,
409
+ "reward": 0.0,
410
+ "reward_std": 0.0,
411
+ "rewards/answer_format_reward": 0.0,
412
+ "rewards/common_format_reward": 0.0,
413
+ "rewards/doors_consistency_reward": 0.0,
414
+ "rewards/geometry_consistency_reward": 0.0,
415
+ "rewards/prompt_consistency_reward": 0.0,
416
+ "rewards/walls_consistency_reward": 0.0,
417
+ "step": 24
418
+ },
419
+ {
420
+ "completion_length": 206.755859375,
421
+ "epoch": 0.020143015409406786,
422
+ "grad_norm": 0.0,
423
+ "kl": 0.0,
424
+ "learning_rate": 9.798549556809026e-07,
425
+ "loss": 0.0,
426
+ "reward": 0.0,
427
+ "reward_std": 0.0,
428
+ "rewards/answer_format_reward": 0.0,
429
+ "rewards/common_format_reward": 0.0,
430
+ "rewards/doors_consistency_reward": 0.0,
431
+ "rewards/geometry_consistency_reward": 0.0,
432
+ "rewards/prompt_consistency_reward": 0.0,
433
+ "rewards/walls_consistency_reward": 0.0,
434
+ "step": 25
435
+ },
436
+ {
437
+ "completion_length": 214.669921875,
438
+ "epoch": 0.02094873602578306,
439
+ "grad_norm": 0.0,
440
+ "kl": 0.0,
441
+ "learning_rate": 9.790491539081385e-07,
442
+ "loss": 0.0,
443
+ "reward": 0.0,
444
+ "reward_std": 0.0,
445
+ "rewards/answer_format_reward": 0.0,
446
+ "rewards/common_format_reward": 0.0,
447
+ "rewards/doors_consistency_reward": 0.0,
448
+ "rewards/geometry_consistency_reward": 0.0,
449
+ "rewards/prompt_consistency_reward": 0.0,
450
+ "rewards/walls_consistency_reward": 0.0,
451
+ "step": 26
452
+ },
453
+ {
454
+ "completion_length": 205.4453125,
455
+ "epoch": 0.02175445664215933,
456
+ "grad_norm": 0.0,
457
+ "kl": 0.0,
458
+ "learning_rate": 9.782433521353746e-07,
459
+ "loss": 0.0,
460
+ "reward": 0.0,
461
+ "reward_std": 0.0,
462
+ "rewards/answer_format_reward": 0.0,
463
+ "rewards/common_format_reward": 0.0,
464
+ "rewards/doors_consistency_reward": 0.0,
465
+ "rewards/geometry_consistency_reward": 0.0,
466
+ "rewards/prompt_consistency_reward": 0.0,
467
+ "rewards/walls_consistency_reward": 0.0,
468
+ "step": 27
469
+ },
470
+ {
471
+ "completion_length": 205.861328125,
472
+ "epoch": 0.022560177258535603,
473
+ "grad_norm": 0.0,
474
+ "kl": 0.0,
475
+ "learning_rate": 9.774375503626108e-07,
476
+ "loss": 0.0,
477
+ "reward": 0.0,
478
+ "reward_std": 0.0,
479
+ "rewards/answer_format_reward": 0.0,
480
+ "rewards/common_format_reward": 0.0,
481
+ "rewards/doors_consistency_reward": 0.0,
482
+ "rewards/geometry_consistency_reward": 0.0,
483
+ "rewards/prompt_consistency_reward": 0.0,
484
+ "rewards/walls_consistency_reward": 0.0,
485
+ "step": 28
486
+ },
487
+ {
488
+ "completion_length": 206.03125,
489
+ "epoch": 0.023365897874911876,
490
+ "grad_norm": 0.0,
491
+ "kl": 0.0,
492
+ "learning_rate": 9.76631748589847e-07,
493
+ "loss": 0.0,
494
+ "reward": 0.0,
495
+ "reward_std": 0.0,
496
+ "rewards/answer_format_reward": 0.0,
497
+ "rewards/common_format_reward": 0.0,
498
+ "rewards/doors_consistency_reward": 0.0,
499
+ "rewards/geometry_consistency_reward": 0.0,
500
+ "rewards/prompt_consistency_reward": 0.0,
501
+ "rewards/walls_consistency_reward": 0.0,
502
+ "step": 29
503
+ },
504
+ {
505
+ "completion_length": 202.75,
506
+ "epoch": 0.024171618491288144,
507
+ "grad_norm": 0.0,
508
+ "kl": 0.0,
509
+ "learning_rate": 9.75825946817083e-07,
510
+ "loss": 0.0,
511
+ "reward": 0.0,
512
+ "reward_std": 0.0,
513
+ "rewards/answer_format_reward": 0.0,
514
+ "rewards/common_format_reward": 0.0,
515
+ "rewards/doors_consistency_reward": 0.0,
516
+ "rewards/geometry_consistency_reward": 0.0,
517
+ "rewards/prompt_consistency_reward": 0.0,
518
+ "rewards/walls_consistency_reward": 0.0,
519
+ "step": 30
520
+ },
521
+ {
522
+ "completion_length": 207.646484375,
523
+ "epoch": 0.024977339107664417,
524
+ "grad_norm": 0.0,
525
+ "kl": 0.0,
526
+ "learning_rate": 9.75020145044319e-07,
527
+ "loss": 0.0,
528
+ "reward": 0.0,
529
+ "reward_std": 0.0,
530
+ "rewards/answer_format_reward": 0.0,
531
+ "rewards/common_format_reward": 0.0,
532
+ "rewards/doors_consistency_reward": 0.0,
533
+ "rewards/geometry_consistency_reward": 0.0,
534
+ "rewards/prompt_consistency_reward": 0.0,
535
+ "rewards/walls_consistency_reward": 0.0,
536
+ "step": 31
537
+ },
538
+ {
539
+ "completion_length": 210.58203125,
540
+ "epoch": 0.02578305972404069,
541
+ "grad_norm": 0.0,
542
+ "kl": 0.0,
543
+ "learning_rate": 9.742143432715551e-07,
544
+ "loss": 0.0,
545
+ "reward": 0.0,
546
+ "reward_std": 0.0,
547
+ "rewards/answer_format_reward": 0.0,
548
+ "rewards/common_format_reward": 0.0,
549
+ "rewards/doors_consistency_reward": 0.0,
550
+ "rewards/geometry_consistency_reward": 0.0,
551
+ "rewards/prompt_consistency_reward": 0.0,
552
+ "rewards/walls_consistency_reward": 0.0,
553
+ "step": 32
554
+ },
555
+ {
556
+ "completion_length": 206.001953125,
557
+ "epoch": 0.02658878034041696,
558
+ "grad_norm": 0.0,
559
+ "kl": 0.0,
560
+ "learning_rate": 9.734085414987913e-07,
561
+ "loss": 0.0,
562
+ "reward": 0.0,
563
+ "reward_std": 0.0,
564
+ "rewards/answer_format_reward": 0.0,
565
+ "rewards/common_format_reward": 0.0,
566
+ "rewards/doors_consistency_reward": 0.0,
567
+ "rewards/geometry_consistency_reward": 0.0,
568
+ "rewards/prompt_consistency_reward": 0.0,
569
+ "rewards/walls_consistency_reward": 0.0,
570
+ "step": 33
571
+ },
572
+ {
573
+ "completion_length": 204.078125,
574
+ "epoch": 0.027394500956793234,
575
+ "grad_norm": 0.0,
576
+ "kl": 0.0,
577
+ "learning_rate": 9.726027397260274e-07,
578
+ "loss": 0.0,
579
+ "reward": 0.0,
580
+ "reward_std": 0.0,
581
+ "rewards/answer_format_reward": 0.0,
582
+ "rewards/common_format_reward": 0.0,
583
+ "rewards/doors_consistency_reward": 0.0,
584
+ "rewards/geometry_consistency_reward": 0.0,
585
+ "rewards/prompt_consistency_reward": 0.0,
586
+ "rewards/walls_consistency_reward": 0.0,
587
+ "step": 34
588
+ },
589
+ {
590
+ "completion_length": 208.3515625,
591
+ "epoch": 0.028200221573169502,
592
+ "grad_norm": 0.0,
593
+ "kl": 0.0,
594
+ "learning_rate": 9.717969379532635e-07,
595
+ "loss": 0.0,
596
+ "reward": 0.0,
597
+ "reward_std": 0.0,
598
+ "rewards/answer_format_reward": 0.0,
599
+ "rewards/common_format_reward": 0.0,
600
+ "rewards/doors_consistency_reward": 0.0,
601
+ "rewards/geometry_consistency_reward": 0.0,
602
+ "rewards/prompt_consistency_reward": 0.0,
603
+ "rewards/walls_consistency_reward": 0.0,
604
+ "step": 35
605
+ },
606
+ {
607
+ "completion_length": 206.7265625,
608
+ "epoch": 0.029005942189545775,
609
+ "grad_norm": 0.0,
610
+ "kl": 0.0,
611
+ "learning_rate": 9.709911361804995e-07,
612
+ "loss": 0.0,
613
+ "reward": 0.0,
614
+ "reward_std": 0.0,
615
+ "rewards/answer_format_reward": 0.0,
616
+ "rewards/common_format_reward": 0.0,
617
+ "rewards/doors_consistency_reward": 0.0,
618
+ "rewards/geometry_consistency_reward": 0.0,
619
+ "rewards/prompt_consistency_reward": 0.0,
620
+ "rewards/walls_consistency_reward": 0.0,
621
+ "step": 36
622
+ },
623
+ {
624
+ "completion_length": 204.13671875,
625
+ "epoch": 0.029811662805922047,
626
+ "grad_norm": 0.0,
627
+ "kl": 0.0,
628
+ "learning_rate": 9.701853344077356e-07,
629
+ "loss": 0.0,
630
+ "reward": 0.0,
631
+ "reward_std": 0.0,
632
+ "rewards/answer_format_reward": 0.0,
633
+ "rewards/common_format_reward": 0.0,
634
+ "rewards/doors_consistency_reward": 0.0,
635
+ "rewards/geometry_consistency_reward": 0.0,
636
+ "rewards/prompt_consistency_reward": 0.0,
637
+ "rewards/walls_consistency_reward": 0.0,
638
+ "step": 37
639
+ },
640
+ {
641
+ "completion_length": 207.029296875,
642
+ "epoch": 0.03061738342229832,
643
+ "grad_norm": 0.0,
644
+ "kl": 0.0,
645
+ "learning_rate": 9.693795326349717e-07,
646
+ "loss": 0.0,
647
+ "reward": 0.0,
648
+ "reward_std": 0.0,
649
+ "rewards/answer_format_reward": 0.0,
650
+ "rewards/common_format_reward": 0.0,
651
+ "rewards/doors_consistency_reward": 0.0,
652
+ "rewards/geometry_consistency_reward": 0.0,
653
+ "rewards/prompt_consistency_reward": 0.0,
654
+ "rewards/walls_consistency_reward": 0.0,
655
+ "step": 38
656
+ },
657
+ {
658
+ "completion_length": 203.302734375,
659
+ "epoch": 0.03142310403867459,
660
+ "grad_norm": 0.0,
661
+ "kl": 0.0,
662
+ "learning_rate": 9.685737308622079e-07,
663
+ "loss": 0.0,
664
+ "reward": 0.0,
665
+ "reward_std": 0.0,
666
+ "rewards/answer_format_reward": 0.0,
667
+ "rewards/common_format_reward": 0.0,
668
+ "rewards/doors_consistency_reward": 0.0,
669
+ "rewards/geometry_consistency_reward": 0.0,
670
+ "rewards/prompt_consistency_reward": 0.0,
671
+ "rewards/walls_consistency_reward": 0.0,
672
+ "step": 39
673
+ },
674
+ {
675
+ "completion_length": 211.501953125,
676
+ "epoch": 0.032228824655050864,
677
+ "grad_norm": 0.0,
678
+ "kl": 0.0,
679
+ "learning_rate": 9.67767929089444e-07,
680
+ "loss": 0.0,
681
+ "reward": 0.0,
682
+ "reward_std": 0.0,
683
+ "rewards/answer_format_reward": 0.0,
684
+ "rewards/common_format_reward": 0.0,
685
+ "rewards/doors_consistency_reward": 0.0,
686
+ "rewards/geometry_consistency_reward": 0.0,
687
+ "rewards/prompt_consistency_reward": 0.0,
688
+ "rewards/walls_consistency_reward": 0.0,
689
+ "step": 40
690
+ },
691
+ {
692
+ "completion_length": 205.265625,
693
+ "epoch": 0.03303454527142713,
694
+ "grad_norm": 0.0,
695
+ "kl": 0.0,
696
+ "learning_rate": 9.6696212731668e-07,
697
+ "loss": 0.0,
698
+ "reward": 0.0,
699
+ "reward_std": 0.0,
700
+ "rewards/answer_format_reward": 0.0,
701
+ "rewards/common_format_reward": 0.0,
702
+ "rewards/doors_consistency_reward": 0.0,
703
+ "rewards/geometry_consistency_reward": 0.0,
704
+ "rewards/prompt_consistency_reward": 0.0,
705
+ "rewards/walls_consistency_reward": 0.0,
706
+ "step": 41
707
+ },
708
+ {
709
+ "completion_length": 198.306640625,
710
+ "epoch": 0.0338402658878034,
711
+ "grad_norm": 0.0,
712
+ "kl": 0.0,
713
+ "learning_rate": 9.66156325543916e-07,
714
+ "loss": 0.0,
715
+ "reward": 0.0,
716
+ "reward_std": 0.0,
717
+ "rewards/answer_format_reward": 0.0,
718
+ "rewards/common_format_reward": 0.0,
719
+ "rewards/doors_consistency_reward": 0.0,
720
+ "rewards/geometry_consistency_reward": 0.0,
721
+ "rewards/prompt_consistency_reward": 0.0,
722
+ "rewards/walls_consistency_reward": 0.0,
723
+ "step": 42
724
+ },
725
+ {
726
+ "completion_length": 202.0390625,
727
+ "epoch": 0.034645986504179674,
728
+ "grad_norm": 0.0,
729
+ "kl": 0.0,
730
+ "learning_rate": 9.653505237711522e-07,
731
+ "loss": 0.0,
732
+ "reward": 0.0,
733
+ "reward_std": 0.0,
734
+ "rewards/answer_format_reward": 0.0,
735
+ "rewards/common_format_reward": 0.0,
736
+ "rewards/doors_consistency_reward": 0.0,
737
+ "rewards/geometry_consistency_reward": 0.0,
738
+ "rewards/prompt_consistency_reward": 0.0,
739
+ "rewards/walls_consistency_reward": 0.0,
740
+ "step": 43
741
+ },
742
+ {
743
+ "completion_length": 203.447265625,
744
+ "epoch": 0.035451707120555946,
745
+ "grad_norm": 0.0,
746
+ "kl": 0.0,
747
+ "learning_rate": 9.645447219983884e-07,
748
+ "loss": 0.0,
749
+ "reward": 0.0,
750
+ "reward_std": 0.0,
751
+ "rewards/answer_format_reward": 0.0,
752
+ "rewards/common_format_reward": 0.0,
753
+ "rewards/doors_consistency_reward": 0.0,
754
+ "rewards/geometry_consistency_reward": 0.0,
755
+ "rewards/prompt_consistency_reward": 0.0,
756
+ "rewards/walls_consistency_reward": 0.0,
757
+ "step": 44
758
+ },
759
+ {
760
+ "completion_length": 208.609375,
761
+ "epoch": 0.03625742773693222,
762
+ "grad_norm": 0.0,
763
+ "kl": 0.0,
764
+ "learning_rate": 9.637389202256245e-07,
765
+ "loss": 0.0,
766
+ "reward": 0.0,
767
+ "reward_std": 0.0,
768
+ "rewards/answer_format_reward": 0.0,
769
+ "rewards/common_format_reward": 0.0,
770
+ "rewards/doors_consistency_reward": 0.0,
771
+ "rewards/geometry_consistency_reward": 0.0,
772
+ "rewards/prompt_consistency_reward": 0.0,
773
+ "rewards/walls_consistency_reward": 0.0,
774
+ "step": 45
775
+ },
776
+ {
777
+ "completion_length": 206.298828125,
778
+ "epoch": 0.03706314835330849,
779
+ "grad_norm": 0.0,
780
+ "kl": 0.0,
781
+ "learning_rate": 9.629331184528604e-07,
782
+ "loss": 0.0,
783
+ "reward": 0.0,
784
+ "reward_std": 0.0,
785
+ "rewards/answer_format_reward": 0.0,
786
+ "rewards/common_format_reward": 0.0,
787
+ "rewards/doors_consistency_reward": 0.0,
788
+ "rewards/geometry_consistency_reward": 0.0,
789
+ "rewards/prompt_consistency_reward": 0.0,
790
+ "rewards/walls_consistency_reward": 0.0,
791
+ "step": 46
792
+ },
793
+ {
794
+ "completion_length": 205.087890625,
795
+ "epoch": 0.03786886896968476,
796
+ "grad_norm": 0.0,
797
+ "kl": 0.0,
798
+ "learning_rate": 9.621273166800966e-07,
799
+ "loss": 0.0,
800
+ "reward": 0.0,
801
+ "reward_std": 0.0,
802
+ "rewards/answer_format_reward": 0.0,
803
+ "rewards/common_format_reward": 0.0,
804
+ "rewards/doors_consistency_reward": 0.0,
805
+ "rewards/geometry_consistency_reward": 0.0,
806
+ "rewards/prompt_consistency_reward": 0.0,
807
+ "rewards/walls_consistency_reward": 0.0,
808
+ "step": 47
809
+ },
810
+ {
811
+ "completion_length": 206.744140625,
812
+ "epoch": 0.038674589586061035,
813
+ "grad_norm": 0.0,
814
+ "kl": 0.0,
815
+ "learning_rate": 9.613215149073327e-07,
816
+ "loss": 0.0,
817
+ "reward": 0.0,
818
+ "reward_std": 0.0,
819
+ "rewards/answer_format_reward": 0.0,
820
+ "rewards/common_format_reward": 0.0,
821
+ "rewards/doors_consistency_reward": 0.0,
822
+ "rewards/geometry_consistency_reward": 0.0,
823
+ "rewards/prompt_consistency_reward": 0.0,
824
+ "rewards/walls_consistency_reward": 0.0,
825
+ "step": 48
826
+ },
827
+ {
828
+ "completion_length": 202.36328125,
829
+ "epoch": 0.03948031020243731,
830
+ "grad_norm": 0.0,
831
+ "kl": 0.0,
832
+ "learning_rate": 9.605157131345689e-07,
833
+ "loss": 0.0,
834
+ "reward": 0.0,
835
+ "reward_std": 0.0,
836
+ "rewards/answer_format_reward": 0.0,
837
+ "rewards/common_format_reward": 0.0,
838
+ "rewards/doors_consistency_reward": 0.0,
839
+ "rewards/geometry_consistency_reward": 0.0,
840
+ "rewards/prompt_consistency_reward": 0.0,
841
+ "rewards/walls_consistency_reward": 0.0,
842
+ "step": 49
843
+ },
844
+ {
845
+ "completion_length": 208.775390625,
846
+ "epoch": 0.04028603081881357,
847
+ "grad_norm": 0.0,
848
+ "kl": 0.0,
849
+ "learning_rate": 9.59709911361805e-07,
850
+ "loss": 0.0,
851
+ "reward": 0.0,
852
+ "reward_std": 0.0,
853
+ "rewards/answer_format_reward": 0.0,
854
+ "rewards/common_format_reward": 0.0,
855
+ "rewards/doors_consistency_reward": 0.0,
856
+ "rewards/geometry_consistency_reward": 0.0,
857
+ "rewards/prompt_consistency_reward": 0.0,
858
+ "rewards/walls_consistency_reward": 0.0,
859
+ "step": 50
860
+ },
861
+ {
862
+ "completion_length": 201.9296875,
863
+ "epoch": 0.041091751435189845,
864
+ "grad_norm": 0.0,
865
+ "kl": 0.0,
866
+ "learning_rate": 9.58904109589041e-07,
867
+ "loss": 0.0,
868
+ "reward": 0.0,
869
+ "reward_std": 0.0,
870
+ "rewards/answer_format_reward": 0.0,
871
+ "rewards/common_format_reward": 0.0,
872
+ "rewards/doors_consistency_reward": 0.0,
873
+ "rewards/geometry_consistency_reward": 0.0,
874
+ "rewards/prompt_consistency_reward": 0.0,
875
+ "rewards/walls_consistency_reward": 0.0,
876
+ "step": 51
877
+ },
878
+ {
879
+ "completion_length": 202.755859375,
880
+ "epoch": 0.04189747205156612,
881
+ "grad_norm": 0.0,
882
+ "kl": 0.0,
883
+ "learning_rate": 9.580983078162773e-07,
884
+ "loss": 0.0,
885
+ "reward": 0.0,
886
+ "reward_std": 0.0,
887
+ "rewards/answer_format_reward": 0.0,
888
+ "rewards/common_format_reward": 0.0,
889
+ "rewards/doors_consistency_reward": 0.0,
890
+ "rewards/geometry_consistency_reward": 0.0,
891
+ "rewards/prompt_consistency_reward": 0.0,
892
+ "rewards/walls_consistency_reward": 0.0,
893
+ "step": 52
894
+ },
895
+ {
896
+ "completion_length": 200.017578125,
897
+ "epoch": 0.04270319266794239,
898
+ "grad_norm": 0.0,
899
+ "kl": 0.0,
900
+ "learning_rate": 9.572925060435134e-07,
901
+ "loss": 0.0,
902
+ "reward": 0.0,
903
+ "reward_std": 0.0,
904
+ "rewards/answer_format_reward": 0.0,
905
+ "rewards/common_format_reward": 0.0,
906
+ "rewards/doors_consistency_reward": 0.0,
907
+ "rewards/geometry_consistency_reward": 0.0,
908
+ "rewards/prompt_consistency_reward": 0.0,
909
+ "rewards/walls_consistency_reward": 0.0,
910
+ "step": 53
911
+ },
912
+ {
913
+ "completion_length": 205.41015625,
914
+ "epoch": 0.04350891328431866,
915
+ "grad_norm": 0.0,
916
+ "kl": 0.0,
917
+ "learning_rate": 9.564867042707493e-07,
918
+ "loss": 0.0,
919
+ "reward": 0.0,
920
+ "reward_std": 0.0,
921
+ "rewards/answer_format_reward": 0.0,
922
+ "rewards/common_format_reward": 0.0,
923
+ "rewards/doors_consistency_reward": 0.0,
924
+ "rewards/geometry_consistency_reward": 0.0,
925
+ "rewards/prompt_consistency_reward": 0.0,
926
+ "rewards/walls_consistency_reward": 0.0,
927
+ "step": 54
928
+ },
929
+ {
930
+ "completion_length": 203.447265625,
931
+ "epoch": 0.044314633900694934,
932
+ "grad_norm": 0.0,
933
+ "kl": 0.0,
934
+ "learning_rate": 9.556809024979855e-07,
935
+ "loss": 0.0,
936
+ "reward": 0.0,
937
+ "reward_std": 0.0,
938
+ "rewards/answer_format_reward": 0.0,
939
+ "rewards/common_format_reward": 0.0,
940
+ "rewards/doors_consistency_reward": 0.0,
941
+ "rewards/geometry_consistency_reward": 0.0,
942
+ "rewards/prompt_consistency_reward": 0.0,
943
+ "rewards/walls_consistency_reward": 0.0,
944
+ "step": 55
945
+ },
946
+ {
947
+ "completion_length": 205.23046875,
948
+ "epoch": 0.04512035451707121,
949
+ "grad_norm": 0.0,
950
+ "kl": 0.0,
951
+ "learning_rate": 9.548751007252216e-07,
952
+ "loss": 0.0,
953
+ "reward": 0.0,
954
+ "reward_std": 0.0,
955
+ "rewards/answer_format_reward": 0.0,
956
+ "rewards/common_format_reward": 0.0,
957
+ "rewards/doors_consistency_reward": 0.0,
958
+ "rewards/geometry_consistency_reward": 0.0,
959
+ "rewards/prompt_consistency_reward": 0.0,
960
+ "rewards/walls_consistency_reward": 0.0,
961
+ "step": 56
962
+ },
963
+ {
964
+ "completion_length": 203.380859375,
965
+ "epoch": 0.04592607513344748,
966
+ "grad_norm": 0.0,
967
+ "kl": 0.0,
968
+ "learning_rate": 9.540692989524578e-07,
969
+ "loss": 0.0,
970
+ "reward": 0.0,
971
+ "reward_std": 0.0,
972
+ "rewards/answer_format_reward": 0.0,
973
+ "rewards/common_format_reward": 0.0,
974
+ "rewards/doors_consistency_reward": 0.0,
975
+ "rewards/geometry_consistency_reward": 0.0,
976
+ "rewards/prompt_consistency_reward": 0.0,
977
+ "rewards/walls_consistency_reward": 0.0,
978
+ "step": 57
979
+ },
980
+ {
981
+ "completion_length": 207.357421875,
982
+ "epoch": 0.04673179574982375,
983
+ "grad_norm": 0.0,
984
+ "kl": 0.0,
985
+ "learning_rate": 9.532634971796938e-07,
986
+ "loss": 0.0,
987
+ "reward": 0.0,
988
+ "reward_std": 0.0,
989
+ "rewards/answer_format_reward": 0.0,
990
+ "rewards/common_format_reward": 0.0,
991
+ "rewards/doors_consistency_reward": 0.0,
992
+ "rewards/geometry_consistency_reward": 0.0,
993
+ "rewards/prompt_consistency_reward": 0.0,
994
+ "rewards/walls_consistency_reward": 0.0,
995
+ "step": 58
996
+ },
997
+ {
998
+ "completion_length": 202.60546875,
999
+ "epoch": 0.047537516366200024,
1000
+ "grad_norm": 0.0,
1001
+ "kl": 0.0,
1002
+ "learning_rate": 9.524576954069299e-07,
1003
+ "loss": 0.0,
1004
+ "reward": 0.0,
1005
+ "reward_std": 0.0,
1006
+ "rewards/answer_format_reward": 0.0,
1007
+ "rewards/common_format_reward": 0.0,
1008
+ "rewards/doors_consistency_reward": 0.0,
1009
+ "rewards/geometry_consistency_reward": 0.0,
1010
+ "rewards/prompt_consistency_reward": 0.0,
1011
+ "rewards/walls_consistency_reward": 0.0,
1012
+ "step": 59
1013
+ },
1014
+ {
1015
+ "completion_length": 206.6875,
1016
+ "epoch": 0.04834323698257629,
1017
+ "grad_norm": 0.0,
1018
+ "kl": 0.0,
1019
+ "learning_rate": 9.51651893634166e-07,
1020
+ "loss": 0.0,
1021
+ "reward": 0.0,
1022
+ "reward_std": 0.0,
1023
+ "rewards/answer_format_reward": 0.0,
1024
+ "rewards/common_format_reward": 0.0,
1025
+ "rewards/doors_consistency_reward": 0.0,
1026
+ "rewards/geometry_consistency_reward": 0.0,
1027
+ "rewards/prompt_consistency_reward": 0.0,
1028
+ "rewards/walls_consistency_reward": 0.0,
1029
+ "step": 60
1030
+ },
1031
+ {
1032
+ "completion_length": 209.169921875,
1033
+ "epoch": 0.04914895759895256,
1034
+ "grad_norm": 0.0,
1035
+ "kl": 0.0,
1036
+ "learning_rate": 9.508460918614021e-07,
1037
+ "loss": 0.0,
1038
+ "reward": 0.0,
1039
+ "reward_std": 0.0,
1040
+ "rewards/answer_format_reward": 0.0,
1041
+ "rewards/common_format_reward": 0.0,
1042
+ "rewards/doors_consistency_reward": 0.0,
1043
+ "rewards/geometry_consistency_reward": 0.0,
1044
+ "rewards/prompt_consistency_reward": 0.0,
1045
+ "rewards/walls_consistency_reward": 0.0,
1046
+ "step": 61
1047
+ },
1048
+ {
1049
+ "completion_length": 212.3828125,
1050
+ "epoch": 0.049954678215328834,
1051
+ "grad_norm": 0.0,
1052
+ "kl": 0.0,
1053
+ "learning_rate": 9.500402900886381e-07,
1054
+ "loss": 0.0,
1055
+ "reward": 0.0,
1056
+ "reward_std": 0.0,
1057
+ "rewards/answer_format_reward": 0.0,
1058
+ "rewards/common_format_reward": 0.0,
1059
+ "rewards/doors_consistency_reward": 0.0,
1060
+ "rewards/geometry_consistency_reward": 0.0,
1061
+ "rewards/prompt_consistency_reward": 0.0,
1062
+ "rewards/walls_consistency_reward": 0.0,
1063
+ "step": 62
1064
+ },
1065
+ {
1066
+ "completion_length": 206.1484375,
1067
+ "epoch": 0.050760398831705106,
1068
+ "grad_norm": 0.0,
1069
+ "kl": 0.0,
1070
+ "learning_rate": 9.492344883158743e-07,
1071
+ "loss": 0.0,
1072
+ "reward": 0.0,
1073
+ "reward_std": 0.0,
1074
+ "rewards/answer_format_reward": 0.0,
1075
+ "rewards/common_format_reward": 0.0,
1076
+ "rewards/doors_consistency_reward": 0.0,
1077
+ "rewards/geometry_consistency_reward": 0.0,
1078
+ "rewards/prompt_consistency_reward": 0.0,
1079
+ "rewards/walls_consistency_reward": 0.0,
1080
+ "step": 63
1081
+ },
1082
+ {
1083
+ "completion_length": 206.248046875,
1084
+ "epoch": 0.05156611944808138,
1085
+ "grad_norm": 0.0,
1086
+ "kl": 0.0,
1087
+ "learning_rate": 9.484286865431104e-07,
1088
+ "loss": 0.0,
1089
+ "reward": 0.0,
1090
+ "reward_std": 0.0,
1091
+ "rewards/answer_format_reward": 0.0,
1092
+ "rewards/common_format_reward": 0.0,
1093
+ "rewards/doors_consistency_reward": 0.0,
1094
+ "rewards/geometry_consistency_reward": 0.0,
1095
+ "rewards/prompt_consistency_reward": 0.0,
1096
+ "rewards/walls_consistency_reward": 0.0,
1097
+ "step": 64
1098
+ },
1099
+ {
1100
+ "completion_length": 206.1875,
1101
+ "epoch": 0.05237184006445765,
1102
+ "grad_norm": 0.0,
1103
+ "kl": 0.0,
1104
+ "learning_rate": 9.476228847703464e-07,
1105
+ "loss": 0.0,
1106
+ "reward": 0.0,
1107
+ "reward_std": 0.0,
1108
+ "rewards/answer_format_reward": 0.0,
1109
+ "rewards/common_format_reward": 0.0,
1110
+ "rewards/doors_consistency_reward": 0.0,
1111
+ "rewards/geometry_consistency_reward": 0.0,
1112
+ "rewards/prompt_consistency_reward": 0.0,
1113
+ "rewards/walls_consistency_reward": 0.0,
1114
+ "step": 65
1115
+ },
1116
+ {
1117
+ "completion_length": 203.595703125,
1118
+ "epoch": 0.05317756068083392,
1119
+ "grad_norm": 0.0,
1120
+ "kl": 0.0,
1121
+ "learning_rate": 9.468170829975826e-07,
1122
+ "loss": 0.0,
1123
+ "reward": 0.0,
1124
+ "reward_std": 0.0,
1125
+ "rewards/answer_format_reward": 0.0,
1126
+ "rewards/common_format_reward": 0.0,
1127
+ "rewards/doors_consistency_reward": 0.0,
1128
+ "rewards/geometry_consistency_reward": 0.0,
1129
+ "rewards/prompt_consistency_reward": 0.0,
1130
+ "rewards/walls_consistency_reward": 0.0,
1131
+ "step": 66
1132
+ },
1133
+ {
1134
+ "completion_length": 198.89453125,
1135
+ "epoch": 0.053983281297210195,
1136
+ "grad_norm": 0.0,
1137
+ "kl": 0.0,
1138
+ "learning_rate": 9.460112812248186e-07,
1139
+ "loss": 0.0,
1140
+ "reward": 0.0,
1141
+ "reward_std": 0.0,
1142
+ "rewards/answer_format_reward": 0.0,
1143
+ "rewards/common_format_reward": 0.0,
1144
+ "rewards/doors_consistency_reward": 0.0,
1145
+ "rewards/geometry_consistency_reward": 0.0,
1146
+ "rewards/prompt_consistency_reward": 0.0,
1147
+ "rewards/walls_consistency_reward": 0.0,
1148
+ "step": 67
1149
+ },
1150
+ {
1151
+ "completion_length": 205.80078125,
1152
+ "epoch": 0.05478900191358647,
1153
+ "grad_norm": 0.0,
1154
+ "kl": 0.0,
1155
+ "learning_rate": 9.452054794520548e-07,
1156
+ "loss": 0.0,
1157
+ "reward": 0.0,
1158
+ "reward_std": 0.0,
1159
+ "rewards/answer_format_reward": 0.0,
1160
+ "rewards/common_format_reward": 0.0,
1161
+ "rewards/doors_consistency_reward": 0.0,
1162
+ "rewards/geometry_consistency_reward": 0.0,
1163
+ "rewards/prompt_consistency_reward": 0.0,
1164
+ "rewards/walls_consistency_reward": 0.0,
1165
+ "step": 68
1166
+ },
1167
+ {
1168
+ "completion_length": 209.66015625,
1169
+ "epoch": 0.05559472252996273,
1170
+ "grad_norm": 0.0,
1171
+ "kl": 0.0,
1172
+ "learning_rate": 9.443996776792909e-07,
1173
+ "loss": 0.0,
1174
+ "reward": 0.0,
1175
+ "reward_std": 0.0,
1176
+ "rewards/answer_format_reward": 0.0,
1177
+ "rewards/common_format_reward": 0.0,
1178
+ "rewards/doors_consistency_reward": 0.0,
1179
+ "rewards/geometry_consistency_reward": 0.0,
1180
+ "rewards/prompt_consistency_reward": 0.0,
1181
+ "rewards/walls_consistency_reward": 0.0,
1182
+ "step": 69
1183
+ },
1184
+ {
1185
+ "completion_length": 210.0546875,
1186
+ "epoch": 0.056400443146339005,
1187
+ "grad_norm": 0.0,
1188
+ "kl": 0.0,
1189
+ "learning_rate": 9.435938759065269e-07,
1190
+ "loss": 0.0,
1191
+ "reward": 0.0,
1192
+ "reward_std": 0.0,
1193
+ "rewards/answer_format_reward": 0.0,
1194
+ "rewards/common_format_reward": 0.0,
1195
+ "rewards/doors_consistency_reward": 0.0,
1196
+ "rewards/geometry_consistency_reward": 0.0,
1197
+ "rewards/prompt_consistency_reward": 0.0,
1198
+ "rewards/walls_consistency_reward": 0.0,
1199
+ "step": 70
1200
+ },
1201
+ {
1202
+ "completion_length": 207.806640625,
1203
+ "epoch": 0.05720616376271528,
1204
+ "grad_norm": 0.0,
1205
+ "kl": 0.0,
1206
+ "learning_rate": 9.427880741337631e-07,
1207
+ "loss": 0.0,
1208
+ "reward": 0.0,
1209
+ "reward_std": 0.0,
1210
+ "rewards/answer_format_reward": 0.0,
1211
+ "rewards/common_format_reward": 0.0,
1212
+ "rewards/doors_consistency_reward": 0.0,
1213
+ "rewards/geometry_consistency_reward": 0.0,
1214
+ "rewards/prompt_consistency_reward": 0.0,
1215
+ "rewards/walls_consistency_reward": 0.0,
1216
+ "step": 71
1217
+ },
1218
+ {
1219
+ "completion_length": 199.50390625,
1220
+ "epoch": 0.05801188437909155,
1221
+ "grad_norm": 0.0,
1222
+ "kl": 0.0,
1223
+ "learning_rate": 9.419822723609991e-07,
1224
+ "loss": 0.0,
1225
+ "reward": 0.0,
1226
+ "reward_std": 0.0,
1227
+ "rewards/answer_format_reward": 0.0,
1228
+ "rewards/common_format_reward": 0.0,
1229
+ "rewards/doors_consistency_reward": 0.0,
1230
+ "rewards/geometry_consistency_reward": 0.0,
1231
+ "rewards/prompt_consistency_reward": 0.0,
1232
+ "rewards/walls_consistency_reward": 0.0,
1233
+ "step": 72
1234
+ },
1235
+ {
1236
+ "completion_length": 202.6171875,
1237
+ "epoch": 0.05881760499546782,
1238
+ "grad_norm": 0.0,
1239
+ "kl": 0.0,
1240
+ "learning_rate": 9.411764705882352e-07,
1241
+ "loss": 0.0,
1242
+ "reward": 0.0,
1243
+ "reward_std": 0.0,
1244
+ "rewards/answer_format_reward": 0.0,
1245
+ "rewards/common_format_reward": 0.0,
1246
+ "rewards/doors_consistency_reward": 0.0,
1247
+ "rewards/geometry_consistency_reward": 0.0,
1248
+ "rewards/prompt_consistency_reward": 0.0,
1249
+ "rewards/walls_consistency_reward": 0.0,
1250
+ "step": 73
1251
+ },
1252
+ {
1253
+ "completion_length": 206.736328125,
1254
+ "epoch": 0.059623325611844094,
1255
+ "grad_norm": 0.0,
1256
+ "kl": 0.0,
1257
+ "learning_rate": 9.403706688154714e-07,
1258
+ "loss": 0.0,
1259
+ "reward": 0.0,
1260
+ "reward_std": 0.0,
1261
+ "rewards/answer_format_reward": 0.0,
1262
+ "rewards/common_format_reward": 0.0,
1263
+ "rewards/doors_consistency_reward": 0.0,
1264
+ "rewards/geometry_consistency_reward": 0.0,
1265
+ "rewards/prompt_consistency_reward": 0.0,
1266
+ "rewards/walls_consistency_reward": 0.0,
1267
+ "step": 74
1268
+ },
1269
+ {
1270
+ "completion_length": 205.4921875,
1271
+ "epoch": 0.060429046228220366,
1272
+ "grad_norm": 0.0,
1273
+ "kl": 0.0,
1274
+ "learning_rate": 9.395648670427074e-07,
1275
+ "loss": 0.0,
1276
+ "reward": 0.0,
1277
+ "reward_std": 0.0,
1278
+ "rewards/answer_format_reward": 0.0,
1279
+ "rewards/common_format_reward": 0.0,
1280
+ "rewards/doors_consistency_reward": 0.0,
1281
+ "rewards/geometry_consistency_reward": 0.0,
1282
+ "rewards/prompt_consistency_reward": 0.0,
1283
+ "rewards/walls_consistency_reward": 0.0,
1284
+ "step": 75
1285
+ },
1286
+ {
1287
+ "completion_length": 206.326171875,
1288
+ "epoch": 0.06123476684459664,
1289
+ "grad_norm": 0.0,
1290
+ "kl": 0.0,
1291
+ "learning_rate": 9.387590652699435e-07,
1292
+ "loss": 0.0,
1293
+ "reward": 0.0,
1294
+ "reward_std": 0.0,
1295
+ "rewards/answer_format_reward": 0.0,
1296
+ "rewards/common_format_reward": 0.0,
1297
+ "rewards/doors_consistency_reward": 0.0,
1298
+ "rewards/geometry_consistency_reward": 0.0,
1299
+ "rewards/prompt_consistency_reward": 0.0,
1300
+ "rewards/walls_consistency_reward": 0.0,
1301
+ "step": 76
1302
+ },
1303
+ {
1304
+ "completion_length": 201.375,
1305
+ "epoch": 0.06204048746097291,
1306
+ "grad_norm": 0.0,
1307
+ "kl": 0.0,
1308
+ "learning_rate": 9.379532634971796e-07,
1309
+ "loss": 0.0,
1310
+ "reward": 0.0,
1311
+ "reward_std": 0.0,
1312
+ "rewards/answer_format_reward": 0.0,
1313
+ "rewards/common_format_reward": 0.0,
1314
+ "rewards/doors_consistency_reward": 0.0,
1315
+ "rewards/geometry_consistency_reward": 0.0,
1316
+ "rewards/prompt_consistency_reward": 0.0,
1317
+ "rewards/walls_consistency_reward": 0.0,
1318
+ "step": 77
1319
+ },
1320
+ {
1321
+ "completion_length": 206.498046875,
1322
+ "epoch": 0.06284620807734918,
1323
+ "grad_norm": 0.0,
1324
+ "kl": 0.0,
1325
+ "learning_rate": 9.371474617244157e-07,
1326
+ "loss": 0.0,
1327
+ "reward": 0.0,
1328
+ "reward_std": 0.0,
1329
+ "rewards/answer_format_reward": 0.0,
1330
+ "rewards/common_format_reward": 0.0,
1331
+ "rewards/doors_consistency_reward": 0.0,
1332
+ "rewards/geometry_consistency_reward": 0.0,
1333
+ "rewards/prompt_consistency_reward": 0.0,
1334
+ "rewards/walls_consistency_reward": 0.0,
1335
+ "step": 78
1336
+ },
1337
+ {
1338
+ "completion_length": 202.626953125,
1339
+ "epoch": 0.06365192869372545,
1340
+ "grad_norm": 0.0,
1341
+ "kl": 0.0,
1342
+ "learning_rate": 9.363416599516519e-07,
1343
+ "loss": 0.0,
1344
+ "reward": 0.0,
1345
+ "reward_std": 0.0,
1346
+ "rewards/answer_format_reward": 0.0,
1347
+ "rewards/common_format_reward": 0.0,
1348
+ "rewards/doors_consistency_reward": 0.0,
1349
+ "rewards/geometry_consistency_reward": 0.0,
1350
+ "rewards/prompt_consistency_reward": 0.0,
1351
+ "rewards/walls_consistency_reward": 0.0,
1352
+ "step": 79
1353
+ },
1354
+ {
1355
+ "completion_length": 210.91015625,
1356
+ "epoch": 0.06445764931010173,
1357
+ "grad_norm": 0.0,
1358
+ "kl": 0.0,
1359
+ "learning_rate": 9.355358581788879e-07,
1360
+ "loss": 0.0,
1361
+ "reward": 0.0,
1362
+ "reward_std": 0.0,
1363
+ "rewards/answer_format_reward": 0.0,
1364
+ "rewards/common_format_reward": 0.0,
1365
+ "rewards/doors_consistency_reward": 0.0,
1366
+ "rewards/geometry_consistency_reward": 0.0,
1367
+ "rewards/prompt_consistency_reward": 0.0,
1368
+ "rewards/walls_consistency_reward": 0.0,
1369
+ "step": 80
1370
+ },
1371
+ {
1372
+ "completion_length": 204.51171875,
1373
+ "epoch": 0.065263369926478,
1374
+ "grad_norm": 0.0,
1375
+ "kl": 0.0,
1376
+ "learning_rate": 9.34730056406124e-07,
1377
+ "loss": 0.0,
1378
+ "reward": 0.0,
1379
+ "reward_std": 0.0,
1380
+ "rewards/answer_format_reward": 0.0,
1381
+ "rewards/common_format_reward": 0.0,
1382
+ "rewards/doors_consistency_reward": 0.0,
1383
+ "rewards/geometry_consistency_reward": 0.0,
1384
+ "rewards/prompt_consistency_reward": 0.0,
1385
+ "rewards/walls_consistency_reward": 0.0,
1386
+ "step": 81
1387
+ },
1388
+ {
1389
+ "completion_length": 201.0859375,
1390
+ "epoch": 0.06606909054285426,
1391
+ "grad_norm": 0.0,
1392
+ "kl": 0.0,
1393
+ "learning_rate": 9.339242546333601e-07,
1394
+ "loss": 0.0,
1395
+ "reward": 0.0,
1396
+ "reward_std": 0.0,
1397
+ "rewards/answer_format_reward": 0.0,
1398
+ "rewards/common_format_reward": 0.0,
1399
+ "rewards/doors_consistency_reward": 0.0,
1400
+ "rewards/geometry_consistency_reward": 0.0,
1401
+ "rewards/prompt_consistency_reward": 0.0,
1402
+ "rewards/walls_consistency_reward": 0.0,
1403
+ "step": 82
1404
+ },
1405
+ {
1406
+ "completion_length": 206.892578125,
1407
+ "epoch": 0.06687481115923054,
1408
+ "grad_norm": 0.0,
1409
+ "kl": 0.0,
1410
+ "learning_rate": 9.331184528605962e-07,
1411
+ "loss": 0.0,
1412
+ "reward": 0.0,
1413
+ "reward_std": 0.0,
1414
+ "rewards/answer_format_reward": 0.0,
1415
+ "rewards/common_format_reward": 0.0,
1416
+ "rewards/doors_consistency_reward": 0.0,
1417
+ "rewards/geometry_consistency_reward": 0.0,
1418
+ "rewards/prompt_consistency_reward": 0.0,
1419
+ "rewards/walls_consistency_reward": 0.0,
1420
+ "step": 83
1421
+ },
1422
+ {
1423
+ "completion_length": 204.578125,
1424
+ "epoch": 0.0676805317756068,
1425
+ "grad_norm": 0.0,
1426
+ "kl": 0.0,
1427
+ "learning_rate": 9.323126510878323e-07,
1428
+ "loss": 0.0,
1429
+ "reward": 0.0,
1430
+ "reward_std": 0.0,
1431
+ "rewards/answer_format_reward": 0.0,
1432
+ "rewards/common_format_reward": 0.0,
1433
+ "rewards/doors_consistency_reward": 0.0,
1434
+ "rewards/geometry_consistency_reward": 0.0,
1435
+ "rewards/prompt_consistency_reward": 0.0,
1436
+ "rewards/walls_consistency_reward": 0.0,
1437
+ "step": 84
1438
+ },
1439
+ {
1440
+ "completion_length": 202.966796875,
1441
+ "epoch": 0.06848625239198308,
1442
+ "grad_norm": 0.0,
1443
+ "kl": 0.0,
1444
+ "learning_rate": 9.315068493150684e-07,
1445
+ "loss": 0.0,
1446
+ "reward": 0.0,
1447
+ "reward_std": 0.0,
1448
+ "rewards/answer_format_reward": 0.0,
1449
+ "rewards/common_format_reward": 0.0,
1450
+ "rewards/doors_consistency_reward": 0.0,
1451
+ "rewards/geometry_consistency_reward": 0.0,
1452
+ "rewards/prompt_consistency_reward": 0.0,
1453
+ "rewards/walls_consistency_reward": 0.0,
1454
+ "step": 85
1455
+ },
1456
+ {
1457
+ "completion_length": 207.12890625,
1458
+ "epoch": 0.06929197300835935,
1459
+ "grad_norm": 0.0,
1460
+ "kl": 0.0,
1461
+ "learning_rate": 9.307010475423045e-07,
1462
+ "loss": 0.0,
1463
+ "reward": 0.0,
1464
+ "reward_std": 0.0,
1465
+ "rewards/answer_format_reward": 0.0,
1466
+ "rewards/common_format_reward": 0.0,
1467
+ "rewards/doors_consistency_reward": 0.0,
1468
+ "rewards/geometry_consistency_reward": 0.0,
1469
+ "rewards/prompt_consistency_reward": 0.0,
1470
+ "rewards/walls_consistency_reward": 0.0,
1471
+ "step": 86
1472
+ },
1473
+ {
1474
+ "completion_length": 207.099609375,
1475
+ "epoch": 0.07009769362473563,
1476
+ "grad_norm": 0.0,
1477
+ "kl": 0.0,
1478
+ "learning_rate": 9.298952457695408e-07,
1479
+ "loss": 0.0,
1480
+ "reward": 0.0,
1481
+ "reward_std": 0.0,
1482
+ "rewards/answer_format_reward": 0.0,
1483
+ "rewards/common_format_reward": 0.0,
1484
+ "rewards/doors_consistency_reward": 0.0,
1485
+ "rewards/geometry_consistency_reward": 0.0,
1486
+ "rewards/prompt_consistency_reward": 0.0,
1487
+ "rewards/walls_consistency_reward": 0.0,
1488
+ "step": 87
1489
+ },
1490
+ {
1491
+ "completion_length": 203.724609375,
1492
+ "epoch": 0.07090341424111189,
1493
+ "grad_norm": 0.0,
1494
+ "kl": 0.0,
1495
+ "learning_rate": 9.290894439967768e-07,
1496
+ "loss": 0.0,
1497
+ "reward": 0.0,
1498
+ "reward_std": 0.0,
1499
+ "rewards/answer_format_reward": 0.0,
1500
+ "rewards/common_format_reward": 0.0,
1501
+ "rewards/doors_consistency_reward": 0.0,
1502
+ "rewards/geometry_consistency_reward": 0.0,
1503
+ "rewards/prompt_consistency_reward": 0.0,
1504
+ "rewards/walls_consistency_reward": 0.0,
1505
+ "step": 88
1506
+ },
1507
+ {
1508
+ "completion_length": 202.583984375,
1509
+ "epoch": 0.07170913485748817,
1510
+ "grad_norm": 0.0,
1511
+ "kl": 0.0,
1512
+ "learning_rate": 9.282836422240129e-07,
1513
+ "loss": 0.0,
1514
+ "reward": 0.0,
1515
+ "reward_std": 0.0,
1516
+ "rewards/answer_format_reward": 0.0,
1517
+ "rewards/common_format_reward": 0.0,
1518
+ "rewards/doors_consistency_reward": 0.0,
1519
+ "rewards/geometry_consistency_reward": 0.0,
1520
+ "rewards/prompt_consistency_reward": 0.0,
1521
+ "rewards/walls_consistency_reward": 0.0,
1522
+ "step": 89
1523
+ },
1524
+ {
1525
+ "completion_length": 209.16796875,
1526
+ "epoch": 0.07251485547386444,
1527
+ "grad_norm": 0.0,
1528
+ "kl": 0.0,
1529
+ "learning_rate": 9.27477840451249e-07,
1530
+ "loss": 0.0,
1531
+ "reward": 0.0,
1532
+ "reward_std": 0.0,
1533
+ "rewards/answer_format_reward": 0.0,
1534
+ "rewards/common_format_reward": 0.0,
1535
+ "rewards/doors_consistency_reward": 0.0,
1536
+ "rewards/geometry_consistency_reward": 0.0,
1537
+ "rewards/prompt_consistency_reward": 0.0,
1538
+ "rewards/walls_consistency_reward": 0.0,
1539
+ "step": 90
1540
+ },
1541
+ {
1542
+ "completion_length": 201.34765625,
1543
+ "epoch": 0.0733205760902407,
1544
+ "grad_norm": 0.0,
1545
+ "kl": 0.0,
1546
+ "learning_rate": 9.266720386784851e-07,
1547
+ "loss": 0.0,
1548
+ "reward": 0.0,
1549
+ "reward_std": 0.0,
1550
+ "rewards/answer_format_reward": 0.0,
1551
+ "rewards/common_format_reward": 0.0,
1552
+ "rewards/doors_consistency_reward": 0.0,
1553
+ "rewards/geometry_consistency_reward": 0.0,
1554
+ "rewards/prompt_consistency_reward": 0.0,
1555
+ "rewards/walls_consistency_reward": 0.0,
1556
+ "step": 91
1557
+ },
1558
+ {
1559
+ "completion_length": 205.546875,
1560
+ "epoch": 0.07412629670661698,
1561
+ "grad_norm": 0.0,
1562
+ "kl": 0.0,
1563
+ "learning_rate": 9.258662369057212e-07,
1564
+ "loss": 0.0,
1565
+ "reward": 0.0,
1566
+ "reward_std": 0.0,
1567
+ "rewards/answer_format_reward": 0.0,
1568
+ "rewards/common_format_reward": 0.0,
1569
+ "rewards/doors_consistency_reward": 0.0,
1570
+ "rewards/geometry_consistency_reward": 0.0,
1571
+ "rewards/prompt_consistency_reward": 0.0,
1572
+ "rewards/walls_consistency_reward": 0.0,
1573
+ "step": 92
1574
+ },
1575
+ {
1576
+ "completion_length": 202.95703125,
1577
+ "epoch": 0.07493201732299325,
1578
+ "grad_norm": 0.0,
1579
+ "kl": 0.0,
1580
+ "learning_rate": 9.250604351329573e-07,
1581
+ "loss": 0.0,
1582
+ "reward": 0.0,
1583
+ "reward_std": 0.0,
1584
+ "rewards/answer_format_reward": 0.0,
1585
+ "rewards/common_format_reward": 0.0,
1586
+ "rewards/doors_consistency_reward": 0.0,
1587
+ "rewards/geometry_consistency_reward": 0.0,
1588
+ "rewards/prompt_consistency_reward": 0.0,
1589
+ "rewards/walls_consistency_reward": 0.0,
1590
+ "step": 93
1591
+ },
1592
+ {
1593
+ "completion_length": 207.23828125,
1594
+ "epoch": 0.07573773793936953,
1595
+ "grad_norm": 0.0,
1596
+ "kl": 0.0,
1597
+ "learning_rate": 9.242546333601934e-07,
1598
+ "loss": 0.0,
1599
+ "reward": 0.0,
1600
+ "reward_std": 0.0,
1601
+ "rewards/answer_format_reward": 0.0,
1602
+ "rewards/common_format_reward": 0.0,
1603
+ "rewards/doors_consistency_reward": 0.0,
1604
+ "rewards/geometry_consistency_reward": 0.0,
1605
+ "rewards/prompt_consistency_reward": 0.0,
1606
+ "rewards/walls_consistency_reward": 0.0,
1607
+ "step": 94
1608
+ },
1609
+ {
1610
+ "completion_length": 207.515625,
1611
+ "epoch": 0.07654345855574579,
1612
+ "grad_norm": 0.0,
1613
+ "kl": 0.0,
1614
+ "learning_rate": 9.234488315874294e-07,
1615
+ "loss": 0.0,
1616
+ "reward": 0.0,
1617
+ "reward_std": 0.0,
1618
+ "rewards/answer_format_reward": 0.0,
1619
+ "rewards/common_format_reward": 0.0,
1620
+ "rewards/doors_consistency_reward": 0.0,
1621
+ "rewards/geometry_consistency_reward": 0.0,
1622
+ "rewards/prompt_consistency_reward": 0.0,
1623
+ "rewards/walls_consistency_reward": 0.0,
1624
+ "step": 95
1625
+ },
1626
+ {
1627
+ "completion_length": 210.25390625,
1628
+ "epoch": 0.07734917917212207,
1629
+ "grad_norm": 0.0,
1630
+ "kl": 0.0,
1631
+ "learning_rate": 9.226430298146656e-07,
1632
+ "loss": 0.0,
1633
+ "reward": 0.0,
1634
+ "reward_std": 0.0,
1635
+ "rewards/answer_format_reward": 0.0,
1636
+ "rewards/common_format_reward": 0.0,
1637
+ "rewards/doors_consistency_reward": 0.0,
1638
+ "rewards/geometry_consistency_reward": 0.0,
1639
+ "rewards/prompt_consistency_reward": 0.0,
1640
+ "rewards/walls_consistency_reward": 0.0,
1641
+ "step": 96
1642
+ },
1643
+ {
1644
+ "completion_length": 205.5546875,
1645
+ "epoch": 0.07815489978849834,
1646
+ "grad_norm": 0.0,
1647
+ "kl": 0.0,
1648
+ "learning_rate": 9.218372280419017e-07,
1649
+ "loss": 0.0,
1650
+ "reward": 0.0,
1651
+ "reward_std": 0.0,
1652
+ "rewards/answer_format_reward": 0.0,
1653
+ "rewards/common_format_reward": 0.0,
1654
+ "rewards/doors_consistency_reward": 0.0,
1655
+ "rewards/geometry_consistency_reward": 0.0,
1656
+ "rewards/prompt_consistency_reward": 0.0,
1657
+ "rewards/walls_consistency_reward": 0.0,
1658
+ "step": 97
1659
+ },
1660
+ {
1661
+ "completion_length": 202.5,
1662
+ "epoch": 0.07896062040487462,
1663
+ "grad_norm": 0.0,
1664
+ "kl": 0.0,
1665
+ "learning_rate": 9.210314262691378e-07,
1666
+ "loss": 0.0,
1667
+ "reward": 0.0,
1668
+ "reward_std": 0.0,
1669
+ "rewards/answer_format_reward": 0.0,
1670
+ "rewards/common_format_reward": 0.0,
1671
+ "rewards/doors_consistency_reward": 0.0,
1672
+ "rewards/geometry_consistency_reward": 0.0,
1673
+ "rewards/prompt_consistency_reward": 0.0,
1674
+ "rewards/walls_consistency_reward": 0.0,
1675
+ "step": 98
1676
+ },
1677
+ {
1678
+ "completion_length": 202.875,
1679
+ "epoch": 0.07976634102125088,
1680
+ "grad_norm": 0.0,
1681
+ "kl": 0.0,
1682
+ "learning_rate": 9.202256244963739e-07,
1683
+ "loss": 0.0,
1684
+ "reward": 0.0,
1685
+ "reward_std": 0.0,
1686
+ "rewards/answer_format_reward": 0.0,
1687
+ "rewards/common_format_reward": 0.0,
1688
+ "rewards/doors_consistency_reward": 0.0,
1689
+ "rewards/geometry_consistency_reward": 0.0,
1690
+ "rewards/prompt_consistency_reward": 0.0,
1691
+ "rewards/walls_consistency_reward": 0.0,
1692
+ "step": 99
1693
+ },
1694
+ {
1695
+ "completion_length": 210.3125,
1696
+ "epoch": 0.08057206163762715,
1697
+ "grad_norm": 0.0,
1698
+ "kl": 0.0,
1699
+ "learning_rate": 9.194198227236099e-07,
1700
+ "loss": 0.0,
1701
+ "reward": 0.0,
1702
+ "reward_std": 0.0,
1703
+ "rewards/answer_format_reward": 0.0,
1704
+ "rewards/common_format_reward": 0.0,
1705
+ "rewards/doors_consistency_reward": 0.0,
1706
+ "rewards/geometry_consistency_reward": 0.0,
1707
+ "rewards/prompt_consistency_reward": 0.0,
1708
+ "rewards/walls_consistency_reward": 0.0,
1709
+ "step": 100
1710
+ }
1711
+ ],
1712
+ "logging_steps": 1,
1713
+ "max_steps": 1241,
1714
+ "num_input_tokens_seen": 0,
1715
+ "num_train_epochs": 1,
1716
+ "save_steps": 100,
1717
+ "stateful_callbacks": {
1718
+ "TrainerControl": {
1719
+ "args": {
1720
+ "should_epoch_stop": false,
1721
+ "should_evaluate": false,
1722
+ "should_log": false,
1723
+ "should_save": true,
1724
+ "should_training_stop": false
1725
+ },
1726
+ "attributes": {}
1727
+ }
1728
+ },
1729
+ "total_flos": 0.0,
1730
+ "train_batch_size": 16,
1731
+ "trial_name": null,
1732
+ "trial_params": null
1733
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0473adabf2590196653084495131f1d2d783006e2decc86837ed554b4de5ae48
3
+ size 5624
last-checkpoint/vocab.json ADDED
The diff for this file is too large to render. See raw diff