Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 7 additions & 0 deletions reproducibility_journal.csv
Original file line number Diff line number Diff line change
Expand Up @@ -48,3 +48,10 @@ ThibaultLSDC,GenericAgent-openai_o1-mini-2024-09-12,weblinx_test,0.0.1.dev13,202
ThibaultLSDC,GenericAgent-meta-llama_llama-3.1-405b-instruct,weblinx_test,0.0.1.dev13,2024-11-07_21-42-30,b9451759-4f0e-492c-a3c8-fa5109d2d9b1,0.079,0.005,0,2650/2650,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,7a5b91e62056fa8fb26efdd2f64f5b25a92b817c,,0.12.0,8633c30c31e6a5a1d5122835c035aa56d18f3f0a,
ThibaultLSDC,GenericAgent-meta-llama_llama-3.1-405b-instruct,workarena_l2_agent_curriculum_eval,0.4.1,2024-11-29_14-28-47,528da1f2-1949-41dc-b988-85f19f435af2,0.072,0.017,2,235/235,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.7,1.39.0,0.3.1,b115b2716d8a6328824684a692ed642297f0b1dc,,0.13.3,70dac253628c476aff1af6a975f27f8563453ad2,
ThibaultLSDC,GenericAgent-meta-llama_llama-3.1-405b-instruct,miniwob,0.13.3,2024-11-29_16-14-00,4d748972-6d35-4489-a197-138b656a7db3,0.646,0.019,0,625/625,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.7,1.39.0,0.3.1,becb4856fb1612f44010fe74ef8155d367ca17fc,,0.13.3,70dac253628c476aff1af6a975f27f8563453ad2,
ThibaultLSDC,GenericAgent-gpt-4o,assistantbench,0.13.1,2024-11-28_19-34-58,d93a2398-2b70-41ce-b989-364fed988d73,0.005,0.003,2,213/214,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.7,1.39.0,0.3.0,32865050045c8c71df35c34ff30a6b420a4e258c, M: src/agentlab/experiments/study.py,0.13.1,None,
ThibaultLSDC,GenericAgent-gpt-4o-mini,assistantbench,0.13.1,2024-11-28_19-34-58,d93a2398-2b70-41ce-b989-364fed988d73,0.002,0.002,1,214/214,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.7,1.39.0,0.3.0,32865050045c8c71df35c34ff30a6b420a4e258c, M: src/agentlab/experiments/study.py,0.13.1,None,
ThibaultLSDC,GenericAgent-meta-llama_llama-3.1-405b-instruct,assistantbench,0.13.1,2024-11-28_19-34-58,d93a2398-2b70-41ce-b989-364fed988d73,0.008,0.003,1,212/214,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.7,1.39.0,0.3.0,32865050045c8c71df35c34ff30a6b420a4e258c, M: src/agentlab/experiments/study.py,0.13.1,None,
ThibaultLSDC,GenericAgent-meta-llama_llama-3.1-70b-instruct,assistantbench,0.13.1,2024-11-28_19-34-58,d93a2398-2b70-41ce-b989-364fed988d73,0.007,0.005,8,206/214,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.7,1.39.0,0.3.0,32865050045c8c71df35c34ff30a6b420a4e258c, M: src/agentlab/experiments/study.py,0.13.1,None,
ThibaultLSDC,GenericAgent-meta-llama_llama-3.1-8b-instruct,assistantbench,0.13.1,2024-11-28_19-34-58,d93a2398-2b70-41ce-b989-364fed988d73,0.001,0.001,15,214/214,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.7,1.39.0,0.3.0,32865050045c8c71df35c34ff30a6b420a4e258c, M: src/agentlab/experiments/study.py,0.13.1,None,
ThibaultLSDC,GenericAgent-anthropic_claude-3.5-sonnet:beta,assistantbench,0.13.1,2024-11-28_19-34-58,d93a2398-2b70-41ce-b989-364fed988d73,0.007,0.003,1,212/214,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.7,1.39.0,0.3.0,32865050045c8c71df35c34ff30a6b420a4e258c, M: src/agentlab/experiments/study.py,0.13.1,None,
ThibaultLSDC,GenericAgent-openai_o1-mini-2024-09-12,assistantbench,0.13.1,2024-11-28_19-34-58,d93a2398-2b70-41ce-b989-364fed988d73,0.009,0.005,1,214/214,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.7,1.39.0,0.3.0,32865050045c8c71df35c34ff30a6b420a4e258c, M: src/agentlab/experiments/study.py,0.13.1,None,
2 changes: 1 addition & 1 deletion src/agentlab/experiments/study.py
Original file line number Diff line number Diff line change
@@ -1,3 +1,4 @@
from abc import ABC, abstractmethod
import gzip
import logging
import pickle
Expand Down Expand Up @@ -405,7 +406,6 @@ def load_most_recent(root_dir: Path = None, contains=None) -> "Study":

def _make_study_name(agent_names, benchmark_names, suffix=None):
"""Make a study name from the agent and benchmark names."""

# extract unique agent and benchmark names
agent_names = list(set(agent_names))
benchmark_names = list(set(benchmark_names))
Expand Down