273 lines
7.0 KiB
Plaintext
273 lines
7.0 KiB
Plaintext
|
|
---------------custom config--------------
|
|
run:
|
|
mode: autoline
|
|
custom_path: None
|
|
gpt:
|
|
model: qwen-max
|
|
key_path: config/key_API.json
|
|
save:
|
|
en: True
|
|
root: /home/zhang/CorrectBench/TBgen_App/output/fsm_ps2/
|
|
autoline:
|
|
result_path: results
|
|
cga:
|
|
enabled: True
|
|
max_iter: 10
|
|
target_coverage: 100.0
|
|
probset:
|
|
path: /home/zhang/CorrectBench/data/HDLBits/HDLBits_data.jsonl
|
|
mutant_path: None
|
|
gptgenRTL_path: None
|
|
more_info_paths: []
|
|
only: ['fsm_ps2']
|
|
exclude: []
|
|
exclude_json: None
|
|
filter: [{}]
|
|
checklist:
|
|
max: 3
|
|
debug:
|
|
max: 5
|
|
reboot: 1
|
|
py_rollback: 2
|
|
onlyrun: TBgensimeval
|
|
promptscript: pychecker
|
|
timeout: 300
|
|
TBcheck:
|
|
rtl_num: 20
|
|
correct_max: 3
|
|
discrim_mode: col_full_wrong
|
|
correct_mode: naive
|
|
rtl_compens_en: True
|
|
rtl_compens_max_iter: 3
|
|
itermax: 10
|
|
update_desc: False
|
|
save_compile: True
|
|
save_finalcodes: True
|
|
error_interruption: False
|
|
------------------------------------------
|
|
------config info (custom + default)------
|
|
run:
|
|
version: 2.0
|
|
author: Ruidi Qiu - Technical University of Munich
|
|
time: 20260413_124637
|
|
custom_path: /home/zhang/CorrectBench/TBgen_App/autoline/../config/custom.yaml
|
|
mode: autoline
|
|
hostname: localhost
|
|
pid: 506064
|
|
pyversion: 3.12.3 (main, Mar 3 2026, 12:15:18) [GCC 13.3.0]
|
|
save:
|
|
en: True
|
|
root: /home/zhang/CorrectBench/TBgen_App/output/fsm_ps2/
|
|
pub:
|
|
prefix: None
|
|
dir: saves/0413~0419/
|
|
subdir:
|
|
log:
|
|
en: True
|
|
dir: logs/
|
|
notes: None
|
|
cfg_pmode: iwantall
|
|
debug_en: False
|
|
level: TRACE
|
|
message:
|
|
en: True
|
|
dir: messages/
|
|
format: json
|
|
iverilog:
|
|
en: True
|
|
subdir: ivcode_nodebug
|
|
load:
|
|
prompt:
|
|
path: config/initial_prompts/prompt1.txt
|
|
pick_idx: []
|
|
stage_template:
|
|
path: config/templates/stage_template0301.txt
|
|
gpt:
|
|
model: qwen-max
|
|
key_path: config/key_API.json
|
|
temperature: None
|
|
json_mode: False
|
|
chatgpt:
|
|
start_form: chat
|
|
one_time_talk: False
|
|
rtlgen_model: qwen-max
|
|
iverilog:
|
|
dir:
|
|
task_id:
|
|
autoline:
|
|
result_path: results
|
|
cga:
|
|
enabled: True
|
|
max_iter: 10
|
|
target_coverage: 100.0
|
|
probset:
|
|
path: /home/zhang/CorrectBench/data/HDLBits/HDLBits_data.jsonl
|
|
mutant_path: None
|
|
gptgenRTL_path: None
|
|
more_info_paths: []
|
|
only: ['fsm_ps2']
|
|
exclude: []
|
|
exclude_json: None
|
|
filter: [{}]
|
|
checklist:
|
|
max: 3
|
|
debug:
|
|
max: 5
|
|
reboot: 1
|
|
py_rollback: 2
|
|
onlyrun: TBgensimeval
|
|
promptscript: pychecker
|
|
timeout: 300
|
|
TBcheck:
|
|
rtl_num: 20
|
|
correct_max: 3
|
|
discrim_mode: col_full_wrong
|
|
correct_mode: naive
|
|
rtl_compens_en: True
|
|
rtl_compens_max_iter: 3
|
|
itermax: 10
|
|
update_desc: False
|
|
save_compile: True
|
|
save_finalcodes: True
|
|
error_interruption: False
|
|
_initialized: True
|
|
------------------------------------------
|
|
|
|
--------------default config--------------
|
|
run:
|
|
version: 2.0
|
|
author: Ruidi Qiu - Technical University of Munich
|
|
time: None
|
|
custom_path: None
|
|
mode: qwen-max
|
|
save:
|
|
en: True
|
|
root: None
|
|
pub:
|
|
prefix: None
|
|
dir: saves/$weekrange$/
|
|
subdir:
|
|
log:
|
|
en: True
|
|
dir: logs/
|
|
notes: None
|
|
cfg_pmode: iwantall
|
|
debug_en: False
|
|
level: TRACE
|
|
message:
|
|
en: True
|
|
dir: messages/
|
|
format: json
|
|
iverilog:
|
|
en: True
|
|
subdir: ivcode_nodebug
|
|
load:
|
|
prompt:
|
|
path: config/initial_prompts/prompt1.txt
|
|
pick_idx: []
|
|
stage_template:
|
|
path: config/templates/stage_template0301.txt
|
|
gpt:
|
|
model: 4o
|
|
key_path: config/key_API.json
|
|
temperature: None
|
|
json_mode: False
|
|
chatgpt:
|
|
start_form: chat
|
|
one_time_talk: False
|
|
rtlgen_model: None
|
|
iverilog:
|
|
dir:
|
|
task_id:
|
|
autoline:
|
|
result_path: results
|
|
cga:
|
|
enabled: True
|
|
max_iter: 10
|
|
target_coverage: 100.0
|
|
probset:
|
|
path: None
|
|
mutant_path: None
|
|
gptgenRTL_path: None
|
|
more_info_paths: []
|
|
only: ['lemmings3', 'lemmings4', 'ece241_2013_q8', '2014_q3fsm', 'm2014_q6', 'review2015_fsm', 'rule110', 'fsm_ps2']
|
|
exclude: []
|
|
exclude_json: None
|
|
filter: [{}]
|
|
checklist:
|
|
max: 3
|
|
debug:
|
|
max: 5
|
|
reboot: 1
|
|
py_rollback: 2
|
|
onlyrun: None
|
|
promptscript: None
|
|
timeout: 300
|
|
TBcheck:
|
|
rtl_num: 20
|
|
correct_max: 3
|
|
discrim_mode: col_full_wrong
|
|
correct_mode: naive
|
|
rtl_compens_en: True
|
|
rtl_compens_max_iter: 3
|
|
itermax: 10
|
|
update_desc: False
|
|
save_compile: True
|
|
save_finalcodes: True
|
|
error_interruption: False
|
|
------------------------------------------
|
|
2026-04-13 12:46:37 | INFO |
|
|
2026-04-13 12:46:37 | INFO | ######################### task 1/1 [fsm_ps2] #########################
|
|
2026-04-13 12:46:53 | INFO | [fsm_ps2] [TBgen] stage_0 ends (16.37s used)
|
|
2026-04-13 12:47:15 | INFO | [fsm_ps2] [TBgen] stage_1 ends (21.62s used)
|
|
2026-04-13 12:48:06 | INFO | [fsm_ps2] [TBgen] stage_2 ends (51.01s used)
|
|
2026-04-13 12:48:33 | INFO | [fsm_ps2] [TBgen] stage_3 ends (27.30s used)
|
|
2026-04-13 12:49:26 | INFO | [fsm_ps2] [TBgen] stage_4 ends (52.74s used)
|
|
2026-04-13 12:49:26 | INFO | [fsm_ps2] [TBgen] stage_checklist ends (0.00s used)
|
|
2026-04-13 12:51:25 | INFO | [fsm_ps2] [TBgen] stage_4b ends (119.09s used)
|
|
2026-04-13 12:51:41 | INFO | [fsm_ps2] [TBgen] stage_5 ends (15.26s used)
|
|
2026-04-13 12:51:41 | ERROR | [fsm_ps2] error when running TBgen, the autoline for this task stopped. error message: name 'self' is not defined | location: autoline/TB_autoline.py, func: run_stages_core, line: 365 | caller: location: autoline/TB_autoline.py, func: run_stages, line: 338
|
|
2026-04-13 12:51:41 | INFO |
|
|
########## Analyze of Chatbench_RunInfo ##########
|
|
|
|
#### pass numbers:
|
|
Eval2 : 0
|
|
Eval1 : 0
|
|
Eval0 : 0
|
|
total : 1 (Failed: 1)
|
|
passed TB by autoline reboot action (from TB3_check): 0
|
|
|
|
#### CGA Coverage Info:
|
|
Average Coverage : 0.00%
|
|
(No coverage data found in JSON)
|
|
|
|
#### tokens and cost:
|
|
average prompt tokens: 9091
|
|
average completion tokens: 7399
|
|
total cost: 0.6258
|
|
average cost: 0.6258
|
|
|
|
#### time:
|
|
average time: 303.49s
|
|
|
|
#### debug info table:
|
|
FUNCTIONAL debug info table:
|
|
(debugged here means functional debugging)
|
|
| un-func-debugged | func-debugged | total |
|
|
failed | 1 | 0 | 1 |
|
|
Eval0 | 0 | 0 | 0 |
|
|
Eval1 | 0 | 0 | 0 |
|
|
Eval2 | 0 | 0 | 0 |
|
|
|
|
#### Eval2 ratio:
|
|
|
|
#### CGA Coverage Detail List:
|
|
Task ID | Coverage
|
|
----------------------------------------
|
|
fsm_ps2 | 0.00%
|
|
|
|
loose Eval2 pass metric applied: 0.8
|
|
|
|
|