39 lines
1.3 KiB
YAML
39 lines
1.3 KiB
YAML
|
# OpenThoughts-TBLite Evaluation -- Docker Backend (Local Compute)
|
||
|
|
#
|
||
|
|
# Runs tasks in Docker containers on the local machine.
|
||
|
|
# Sandboxed like Modal but no cloud costs. Good for dev/testing.
|
||
|
|
#
|
||
|
|
# Usage:
|
||
|
|
# python environments/benchmarks/tblite/tblite_env.py evaluate \
|
||
|
|
# --config environments/benchmarks/tblite/local.yaml
|
||
|
|
#
|
||
|
|
# # Override concurrency:
|
||
|
|
# python environments/benchmarks/tblite/tblite_env.py evaluate \
|
||
|
|
# --config environments/benchmarks/tblite/local.yaml \
|
||
|
|
# --env.eval_concurrency 4
|
||
|
|
|
||
|
|
env:
|
||
|
|
enabled_toolsets: ["terminal", "file"]
|
||
|
|
max_agent_turns: 60
|
||
|
|
max_token_length: 32000
|
||
|
|
agent_temperature: 0.8
|
||
|
|
terminal_backend: "docker"
|
||
|
|
terminal_timeout: 300
|
||
|
|
tool_pool_size: 16
|
||
|
|
dataset_name: "NousResearch/openthoughts-tblite"
|
||
|
|
test_timeout: 600
|
||
|
|
task_timeout: 1200
|
||
|
|
eval_concurrency: 8 # max 8 tasks at once
|
||
|
|
tokenizer_name: "NousResearch/Hermes-3-Llama-3.1-8B"
|
||
|
|
use_wandb: false
|
||
|
|
wandb_name: "openthoughts-tblite-local"
|
||
|
|
ensure_scores_are_not_same: false
|
||
|
|
data_dir_to_save_evals: "environments/benchmarks/evals/openthoughts-tblite-local"
|
||
|
|
|
||
|
|
openai:
|
||
|
|
base_url: "https://openrouter.ai/api/v1"
|
||
|
|
model_name: "anthropic/claude-sonnet-4"
|
||
|
|
server_type: "openai"
|
||
|
|
health_check: false
|
||
|
|
# api_key loaded from OPENROUTER_API_KEY in .env
|