Text Generation
Transformers
Safetensors
English
reasoning
reinforcement-learning
synthetic-data
extrapolation
Instructions to use ZachW/extrapolation_rl with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ZachW/extrapolation_rl with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ZachW/extrapolation_rl")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("ZachW/extrapolation_rl", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use ZachW/extrapolation_rl with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ZachW/extrapolation_rl" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ZachW/extrapolation_rl", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/ZachW/extrapolation_rl
- SGLang
How to use ZachW/extrapolation_rl with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "ZachW/extrapolation_rl" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ZachW/extrapolation_rl", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "ZachW/extrapolation_rl" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ZachW/extrapolation_rl", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use ZachW/extrapolation_rl with Docker Model Runner:
docker model run hf.co/ZachW/extrapolation_rl
Upload extrapolation artifact: opd_ckpt18809_refkl_op11_14_s200_merged_hf far-OOD metrics
Browse files
020305/evals/far_ood/opd_ckpt18809_refkl_op11_14_s200_merged_hf/opd_ckpt18809_refkl_op11_14_s200_merged_hf_metrics.json
ADDED
|
@@ -0,0 +1,904 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"checkpoint": "opd_ckpt18809_refkl_op11_14_s200_merged_hf",
|
| 3 |
+
"id": {
|
| 4 |
+
"answer_accuracy": 0.0,
|
| 5 |
+
"avg_response_len": 0.0,
|
| 6 |
+
"avg_loss": 0.0,
|
| 7 |
+
"count": 0,
|
| 8 |
+
"validation_metrics": {},
|
| 9 |
+
"pass_at_k": {},
|
| 10 |
+
"per_op_pass_at_k": {},
|
| 11 |
+
"per_op_accuracy": {},
|
| 12 |
+
"per_op_avg_response_len": {},
|
| 13 |
+
"per_op_avg_loss": {},
|
| 14 |
+
"per_op_length": {},
|
| 15 |
+
"per_op_loss": {},
|
| 16 |
+
"per_template": {
|
| 17 |
+
"crazy_zootopia": {
|
| 18 |
+
"count": 0,
|
| 19 |
+
"correct": 0,
|
| 20 |
+
"answer_accuracy": 0.0,
|
| 21 |
+
"avg_response_len": 0.0,
|
| 22 |
+
"resp_tokens_sum": 0,
|
| 23 |
+
"pass_at_k": {},
|
| 24 |
+
"per_op_pass_at_k": {}
|
| 25 |
+
},
|
| 26 |
+
"teachers_in_school": {
|
| 27 |
+
"count": 0,
|
| 28 |
+
"correct": 0,
|
| 29 |
+
"answer_accuracy": 0.0,
|
| 30 |
+
"avg_response_len": 0.0,
|
| 31 |
+
"resp_tokens_sum": 0,
|
| 32 |
+
"pass_at_k": {},
|
| 33 |
+
"per_op_pass_at_k": {}
|
| 34 |
+
},
|
| 35 |
+
"movie_festival_awards": {
|
| 36 |
+
"count": 0,
|
| 37 |
+
"correct": 0,
|
| 38 |
+
"answer_accuracy": 0.0,
|
| 39 |
+
"avg_response_len": 0.0,
|
| 40 |
+
"resp_tokens_sum": 0,
|
| 41 |
+
"pass_at_k": {},
|
| 42 |
+
"per_op_pass_at_k": {}
|
| 43 |
+
}
|
| 44 |
+
}
|
| 45 |
+
},
|
| 46 |
+
"ood": {
|
| 47 |
+
"answer_accuracy": 0.002484375,
|
| 48 |
+
"avg_response_len": 297.913984375,
|
| 49 |
+
"avg_loss": 0.0,
|
| 50 |
+
"count": 64000,
|
| 51 |
+
"validation_metrics": {},
|
| 52 |
+
"pass_at_k": {
|
| 53 |
+
"pass@1": 0.002484375,
|
| 54 |
+
"pass@2": 0.004610887096774193,
|
| 55 |
+
"pass@4": 0.008140781423804228,
|
| 56 |
+
"pass@8": 0.013616341851820162,
|
| 57 |
+
"pass@16": 0.022010931899641574,
|
| 58 |
+
"pass@32": 0.0355
|
| 59 |
+
},
|
| 60 |
+
"per_op_pass_at_k": {
|
| 61 |
+
"21": {
|
| 62 |
+
"pass@1": 0.0034375,
|
| 63 |
+
"pass@2": 0.00658266129032258,
|
| 64 |
+
"pass@4": 0.0120952447163515,
|
| 65 |
+
"pass@8": 0.020621523915461622,
|
| 66 |
+
"pass@16": 0.03146551724137931,
|
| 67 |
+
"pass@32": 0.045
|
| 68 |
+
},
|
| 69 |
+
"22": {
|
| 70 |
+
"pass@1": 0.00375,
|
| 71 |
+
"pass@2": 0.007298387096774193,
|
| 72 |
+
"pass@4": 0.013849972191323692,
|
| 73 |
+
"pass@8": 0.02514460511679644,
|
| 74 |
+
"pass@16": 0.0428642936596218,
|
| 75 |
+
"pass@32": 0.07
|
| 76 |
+
},
|
| 77 |
+
"23": {
|
| 78 |
+
"pass@1": 0.00328125,
|
| 79 |
+
"pass@2": 0.005756048387096774,
|
| 80 |
+
"pass@4": 0.009340100111234706,
|
| 81 |
+
"pass@8": 0.014399555061179087,
|
| 82 |
+
"pass@16": 0.02258063710080444,
|
| 83 |
+
"pass@32": 0.035
|
| 84 |
+
},
|
| 85 |
+
"24": {
|
| 86 |
+
"pass@1": 0.00375,
|
| 87 |
+
"pass@2": 0.007298387096774193,
|
| 88 |
+
"pass@4": 0.013872914349276975,
|
| 89 |
+
"pass@8": 0.025402515140279327,
|
| 90 |
+
"pass@16": 0.04447194413545916,
|
| 91 |
+
"pass@32": 0.075
|
| 92 |
+
},
|
| 93 |
+
"25": {
|
| 94 |
+
"pass@1": 0.004375,
|
| 95 |
+
"pass@2": 0.007600806451612902,
|
| 96 |
+
"pass@4": 0.011979838709677419,
|
| 97 |
+
"pass@8": 0.017230994552351615,
|
| 98 |
+
"pass@16": 0.024997952636584934,
|
| 99 |
+
"pass@32": 0.04
|
| 100 |
+
},
|
| 101 |
+
"26": {
|
| 102 |
+
"pass@1": 0.00203125,
|
| 103 |
+
"pass@2": 0.0035080645161290323,
|
| 104 |
+
"pass@4": 0.005417825361512791,
|
| 105 |
+
"pass@8": 0.007403268589030548,
|
| 106 |
+
"pass@16": 0.009999830729796393,
|
| 107 |
+
"pass@32": 0.015
|
| 108 |
+
},
|
| 109 |
+
"27": {
|
| 110 |
+
"pass@1": 0.0015625,
|
| 111 |
+
"pass@2": 0.002973790322580645,
|
| 112 |
+
"pass@4": 0.005421301446051168,
|
| 113 |
+
"pass@8": 0.009257353849956742,
|
| 114 |
+
"pass@16": 0.014955815103201089,
|
| 115 |
+
"pass@32": 0.025
|
| 116 |
+
},
|
| 117 |
+
"28": {
|
| 118 |
+
"pass@1": 0.00125,
|
| 119 |
+
"pass@2": 0.0022883064516129033,
|
| 120 |
+
"pass@4": 0.003866101223581757,
|
| 121 |
+
"pass@8": 0.00573586035766236,
|
| 122 |
+
"pass@16": 0.007483005808923495,
|
| 123 |
+
"pass@32": 0.01
|
| 124 |
+
},
|
| 125 |
+
"29": {
|
| 126 |
+
"pass@1": 0.0009375,
|
| 127 |
+
"pass@2": 0.0018649193548387095,
|
| 128 |
+
"pass@4": 0.0036895161290322583,
|
| 129 |
+
"pass@8": 0.0072177419354838715,
|
| 130 |
+
"pass@16": 0.01379032258064516,
|
| 131 |
+
"pass@32": 0.025
|
| 132 |
+
},
|
| 133 |
+
"30": {
|
| 134 |
+
"pass@1": 0.00046875,
|
| 135 |
+
"pass@2": 0.0009375,
|
| 136 |
+
"pass@4": 0.001875,
|
| 137 |
+
"pass@8": 0.00375,
|
| 138 |
+
"pass@16": 0.0075,
|
| 139 |
+
"pass@32": 0.015
|
| 140 |
+
}
|
| 141 |
+
},
|
| 142 |
+
"per_op_accuracy": {
|
| 143 |
+
"21": 0.0034375,
|
| 144 |
+
"22": 0.00375,
|
| 145 |
+
"23": 0.00328125,
|
| 146 |
+
"24": 0.00375,
|
| 147 |
+
"25": 0.004375,
|
| 148 |
+
"26": 0.00203125,
|
| 149 |
+
"27": 0.0015625,
|
| 150 |
+
"28": 0.00125,
|
| 151 |
+
"29": 0.0009375,
|
| 152 |
+
"30": 0.00046875
|
| 153 |
+
},
|
| 154 |
+
"per_op_avg_response_len": {
|
| 155 |
+
"21": 291.64796875,
|
| 156 |
+
"22": 295.7371875,
|
| 157 |
+
"23": 293.74296875,
|
| 158 |
+
"24": 300.16828125,
|
| 159 |
+
"25": 297.91453125,
|
| 160 |
+
"26": 304.6490625,
|
| 161 |
+
"27": 304.83328125,
|
| 162 |
+
"28": 294.66640625,
|
| 163 |
+
"29": 299.793125,
|
| 164 |
+
"30": 295.98703125
|
| 165 |
+
},
|
| 166 |
+
"per_op_avg_loss": {},
|
| 167 |
+
"per_op_length": {
|
| 168 |
+
"21": 291.64796875,
|
| 169 |
+
"22": 295.7371875,
|
| 170 |
+
"23": 293.74296875,
|
| 171 |
+
"24": 300.16828125,
|
| 172 |
+
"25": 297.91453125,
|
| 173 |
+
"26": 304.6490625,
|
| 174 |
+
"27": 304.83328125,
|
| 175 |
+
"28": 294.66640625,
|
| 176 |
+
"29": 299.793125,
|
| 177 |
+
"30": 295.98703125
|
| 178 |
+
},
|
| 179 |
+
"per_op_loss": {},
|
| 180 |
+
"per_template": {
|
| 181 |
+
"crazy_zootopia": {
|
| 182 |
+
"count": 23072,
|
| 183 |
+
"correct": 61,
|
| 184 |
+
"answer_accuracy": 0.0026438973647711513,
|
| 185 |
+
"avg_response_len": 276.247572815534,
|
| 186 |
+
"resp_tokens_sum": 6373584,
|
| 187 |
+
"pass_at_k": {
|
| 188 |
+
"pass@1": 0.0026438973647711513,
|
| 189 |
+
"pass@2": 0.004840387454700014,
|
| 190 |
+
"pass@4": 0.008337704553834667,
|
| 191 |
+
"pass@8": 0.013432497404332345,
|
| 192 |
+
"pass@16": 0.020918036351159127,
|
| 193 |
+
"pass@32": 0.033287101248266296
|
| 194 |
+
},
|
| 195 |
+
"per_op_pass_at_k": {
|
| 196 |
+
"21": {
|
| 197 |
+
"pass@1": 0.0011867088607594937,
|
| 198 |
+
"pass@2": 0.0023734177215189874,
|
| 199 |
+
"pass@4": 0.004746835443037975,
|
| 200 |
+
"pass@8": 0.00949367088607595,
|
| 201 |
+
"pass@16": 0.0189873417721519,
|
| 202 |
+
"pass@32": 0.0379746835443038
|
| 203 |
+
},
|
| 204 |
+
"22": {
|
| 205 |
+
"pass@1": 0.00390625,
|
| 206 |
+
"pass@2": 0.007560483870967741,
|
| 207 |
+
"pass@4": 0.014168520578420465,
|
| 208 |
+
"pass@8": 0.024950562353231984,
|
| 209 |
+
"pass@16": 0.03939562476826103,
|
| 210 |
+
"pass@32": 0.05555555555555555
|
| 211 |
+
},
|
| 212 |
+
"23": {
|
| 213 |
+
"pass@1": 0.0004734848484848485,
|
| 214 |
+
"pass@2": 0.000946969696969697,
|
| 215 |
+
"pass@4": 0.001893939393939394,
|
| 216 |
+
"pass@8": 0.003787878787878788,
|
| 217 |
+
"pass@16": 0.007575757575757576,
|
| 218 |
+
"pass@32": 0.015151515151515152
|
| 219 |
+
},
|
| 220 |
+
"24": {
|
| 221 |
+
"pass@1": 0.006161971830985915,
|
| 222 |
+
"pass@2": 0.011869604725124942,
|
| 223 |
+
"pass@4": 0.02214314809882655,
|
| 224 |
+
"pass@8": 0.03936646700124117,
|
| 225 |
+
"pass@16": 0.06689052868689084,
|
| 226 |
+
"pass@32": 0.11267605633802817
|
| 227 |
+
},
|
| 228 |
+
"25": {
|
| 229 |
+
"pass@1": 0.011408730158730158,
|
| 230 |
+
"pass@2": 0.019169226830517153,
|
| 231 |
+
"pass@4": 0.028110599078341014,
|
| 232 |
+
"pass@8": 0.0348603001661956,
|
| 233 |
+
"pass@16": 0.03967604011614265,
|
| 234 |
+
"pass@32": 0.047619047619047616
|
| 235 |
+
},
|
| 236 |
+
"26": {
|
| 237 |
+
"pass@1": 0.0,
|
| 238 |
+
"pass@2": 0.0,
|
| 239 |
+
"pass@4": 0.0,
|
| 240 |
+
"pass@8": 0.0,
|
| 241 |
+
"pass@16": 0.0,
|
| 242 |
+
"pass@32": 0.0
|
| 243 |
+
},
|
| 244 |
+
"27": {
|
| 245 |
+
"pass@1": 0.00043402777777777775,
|
| 246 |
+
"pass@2": 0.0008680555555555555,
|
| 247 |
+
"pass@4": 0.001736111111111111,
|
| 248 |
+
"pass@8": 0.003472222222222222,
|
| 249 |
+
"pass@16": 0.006944444444444444,
|
| 250 |
+
"pass@32": 0.013888888888888888
|
| 251 |
+
},
|
| 252 |
+
"28": {
|
| 253 |
+
"pass@1": 0.0028735632183908046,
|
| 254 |
+
"pass@2": 0.005260474601408972,
|
| 255 |
+
"pass@4": 0.008887589019728177,
|
| 256 |
+
"pass@8": 0.013185885879683586,
|
| 257 |
+
"pass@16": 0.017202312204421828,
|
| 258 |
+
"pass@32": 0.022988505747126436
|
| 259 |
+
},
|
| 260 |
+
"29": {
|
| 261 |
+
"pass@1": 0.0004166666666666667,
|
| 262 |
+
"pass@2": 0.0008333333333333334,
|
| 263 |
+
"pass@4": 0.0016666666666666668,
|
| 264 |
+
"pass@8": 0.0033333333333333335,
|
| 265 |
+
"pass@16": 0.006666666666666667,
|
| 266 |
+
"pass@32": 0.013333333333333334
|
| 267 |
+
},
|
| 268 |
+
"30": {
|
| 269 |
+
"pass@1": 0.0004464285714285714,
|
| 270 |
+
"pass@2": 0.0008928571428571428,
|
| 271 |
+
"pass@4": 0.0017857142857142857,
|
| 272 |
+
"pass@8": 0.0035714285714285713,
|
| 273 |
+
"pass@16": 0.007142857142857143,
|
| 274 |
+
"pass@32": 0.014285714285714285
|
| 275 |
+
}
|
| 276 |
+
}
|
| 277 |
+
},
|
| 278 |
+
"teachers_in_school": {
|
| 279 |
+
"count": 19936,
|
| 280 |
+
"correct": 29,
|
| 281 |
+
"answer_accuracy": 0.0014546548956661316,
|
| 282 |
+
"avg_response_len": 290.34595706260035,
|
| 283 |
+
"resp_tokens_sum": 5788337,
|
| 284 |
+
"pass_at_k": {
|
| 285 |
+
"pass@1": 0.0014546548956661316,
|
| 286 |
+
"pass@2": 0.0028607673587738823,
|
| 287 |
+
"pass@4": 0.005535087139803991,
|
| 288 |
+
"pass@8": 0.0103836615322536,
|
| 289 |
+
"pass@16": 0.018455498083299257,
|
| 290 |
+
"pass@32": 0.030497592295345103
|
| 291 |
+
},
|
| 292 |
+
"per_op_pass_at_k": {
|
| 293 |
+
"21": {
|
| 294 |
+
"pass@1": 0.004326923076923077,
|
| 295 |
+
"pass@2": 0.008374689826302729,
|
| 296 |
+
"pass@4": 0.015694361256096516,
|
| 297 |
+
"pass@8": 0.027637545991272352,
|
| 298 |
+
"pass@16": 0.0436382305125353,
|
| 299 |
+
"pass@32": 0.06153846153846154
|
| 300 |
+
},
|
| 301 |
+
"22": {
|
| 302 |
+
"pass@1": 0.0030737704918032786,
|
| 303 |
+
"pass@2": 0.006114489687995769,
|
| 304 |
+
"pass@4": 0.012096774193548387,
|
| 305 |
+
"pass@8": 0.023664727657324167,
|
| 306 |
+
"pass@16": 0.0452141723955579,
|
| 307 |
+
"pass@32": 0.08196721311475409
|
| 308 |
+
},
|
| 309 |
+
"23": {
|
| 310 |
+
"pass@1": 0.0013392857142857143,
|
| 311 |
+
"pass@2": 0.0026497695852534552,
|
| 312 |
+
"pass@4": 0.005184331797235023,
|
| 313 |
+
"pass@8": 0.00990783410138249,
|
| 314 |
+
"pass@16": 0.017972350230414748,
|
| 315 |
+
"pass@32": 0.02857142857142857
|
| 316 |
+
},
|
| 317 |
+
"24": {
|
| 318 |
+
"pass@1": 0.0027901785714285715,
|
| 319 |
+
"pass@2": 0.005472350230414745,
|
| 320 |
+
"pass@4": 0.010527073732718894,
|
| 321 |
+
"pass@8": 0.019498847926267278,
|
| 322 |
+
"pass@16": 0.03369815668202765,
|
| 323 |
+
"pass@32": 0.05357142857142857
|
| 324 |
+
},
|
| 325 |
+
"25": {
|
| 326 |
+
"pass@1": 0.0004280821917808219,
|
| 327 |
+
"pass@2": 0.0008561643835616438,
|
| 328 |
+
"pass@4": 0.0017123287671232876,
|
| 329 |
+
"pass@8": 0.003424657534246575,
|
| 330 |
+
"pass@16": 0.00684931506849315,
|
| 331 |
+
"pass@32": 0.0136986301369863
|
| 332 |
+
},
|
| 333 |
+
"26": {
|
| 334 |
+
"pass@1": 0.0006127450980392157,
|
| 335 |
+
"pass@2": 0.0012254901960784314,
|
| 336 |
+
"pass@4": 0.0024509803921568627,
|
| 337 |
+
"pass@8": 0.004901960784313725,
|
| 338 |
+
"pass@16": 0.00980392156862745,
|
| 339 |
+
"pass@32": 0.0196078431372549
|
| 340 |
+
},
|
| 341 |
+
"27": {
|
| 342 |
+
"pass@1": 0.0005387931034482759,
|
| 343 |
+
"pass@2": 0.0010775862068965517,
|
| 344 |
+
"pass@4": 0.0021551724137931034,
|
| 345 |
+
"pass@8": 0.004310344827586207,
|
| 346 |
+
"pass@16": 0.008620689655172414,
|
| 347 |
+
"pass@32": 0.017241379310344827
|
| 348 |
+
},
|
| 349 |
+
"28": {
|
| 350 |
+
"pass@1": 0.0,
|
| 351 |
+
"pass@2": 0.0,
|
| 352 |
+
"pass@4": 0.0,
|
| 353 |
+
"pass@8": 0.0,
|
| 354 |
+
"pass@16": 0.0,
|
| 355 |
+
"pass@32": 0.0
|
| 356 |
+
},
|
| 357 |
+
"29": {
|
| 358 |
+
"pass@1": 0.0014423076923076924,
|
| 359 |
+
"pass@2": 0.002853598014888337,
|
| 360 |
+
"pass@4": 0.005583126550868486,
|
| 361 |
+
"pass@8": 0.010669975186104219,
|
| 362 |
+
"pass@16": 0.01935483870967742,
|
| 363 |
+
"pass@32": 0.03076923076923077
|
| 364 |
+
},
|
| 365 |
+
"30": {
|
| 366 |
+
"pass@1": 0.0,
|
| 367 |
+
"pass@2": 0.0,
|
| 368 |
+
"pass@4": 0.0,
|
| 369 |
+
"pass@8": 0.0,
|
| 370 |
+
"pass@16": 0.0,
|
| 371 |
+
"pass@32": 0.0
|
| 372 |
+
}
|
| 373 |
+
}
|
| 374 |
+
},
|
| 375 |
+
"movie_festival_awards": {
|
| 376 |
+
"count": 20992,
|
| 377 |
+
"correct": 69,
|
| 378 |
+
"answer_accuracy": 0.003286966463414634,
|
| 379 |
+
"avg_response_len": 328.9145388719512,
|
| 380 |
+
"resp_tokens_sum": 6904574,
|
| 381 |
+
"pass_at_k": {
|
| 382 |
+
"pass@1": 0.003286966463414634,
|
| 383 |
+
"pass@2": 0.0060207267899291895,
|
| 384 |
+
"pass@4": 0.010398961244200873,
|
| 385 |
+
"pass@8": 0.016888463323967543,
|
| 386 |
+
"pass@16": 0.026588695555185955,
|
| 387 |
+
"pass@32": 0.042682926829268296
|
| 388 |
+
},
|
| 389 |
+
"per_op_pass_at_k": {
|
| 390 |
+
"21": {
|
| 391 |
+
"pass@1": 0.005580357142857143,
|
| 392 |
+
"pass@2": 0.010440668202764977,
|
| 393 |
+
"pass@4": 0.01828420467185762,
|
| 394 |
+
"pass@8": 0.028176148101064676,
|
| 395 |
+
"pass@16": 0.03493961544573335,
|
| 396 |
+
"pass@32": 0.03571428571428571
|
| 397 |
+
},
|
| 398 |
+
"22": {
|
| 399 |
+
"pass@1": 0.004197761194029851,
|
| 400 |
+
"pass@2": 0.008094607607125662,
|
| 401 |
+
"pass@4": 0.015103846728537512,
|
| 402 |
+
"pass@8": 0.026700479803430013,
|
| 403 |
+
"pass@16": 0.04445237660418707,
|
| 404 |
+
"pass@32": 0.07462686567164178
|
| 405 |
+
},
|
| 406 |
+
"23": {
|
| 407 |
+
"pass@1": 0.00830078125,
|
| 408 |
+
"pass@2": 0.014112903225806451,
|
| 409 |
+
"pass@4": 0.021564324944382644,
|
| 410 |
+
"pass@8": 0.030255666017797552,
|
| 411 |
+
"pass@16": 0.04309473287549774,
|
| 412 |
+
"pass@32": 0.0625
|
| 413 |
+
},
|
| 414 |
+
"24": {
|
| 415 |
+
"pass@1": 0.0021404109589041095,
|
| 416 |
+
"pass@2": 0.0042532037118868755,
|
| 417 |
+
"pass@4": 0.008395934600088379,
|
| 418 |
+
"pass@8": 0.016349977905435263,
|
| 419 |
+
"pass@16": 0.030932390631904547,
|
| 420 |
+
"pass@32": 0.0547945205479452
|
| 421 |
+
},
|
| 422 |
+
"25": {
|
| 423 |
+
"pass@1": 0.001953125,
|
| 424 |
+
"pass@2": 0.00390625,
|
| 425 |
+
"pass@4": 0.0078125,
|
| 426 |
+
"pass@8": 0.015625,
|
| 427 |
+
"pass@16": 0.03125,
|
| 428 |
+
"pass@32": 0.0625
|
| 429 |
+
},
|
| 430 |
+
"26": {
|
| 431 |
+
"pass@1": 0.004518072289156626,
|
| 432 |
+
"pass@2": 0.007700155460551886,
|
| 433 |
+
"pass@4": 0.01154897677472962,
|
| 434 |
+
"pass@8": 0.014827153226579631,
|
| 435 |
+
"pass@16": 0.018071881276617813,
|
| 436 |
+
"pass@32": 0.024096385542168676
|
| 437 |
+
},
|
| 438 |
+
"27": {
|
| 439 |
+
"pass@1": 0.0035714285714285713,
|
| 440 |
+
"pass@2": 0.0067108294930875575,
|
| 441 |
+
"pass@4": 0.011918004131574764,
|
| 442 |
+
"pass@8": 0.01930672528559069,
|
| 443 |
+
"pass@16": 0.028445186009145966,
|
| 444 |
+
"pass@32": 0.04285714285714286
|
| 445 |
+
},
|
| 446 |
+
"28": {
|
| 447 |
+
"pass@1": 0.0,
|
| 448 |
+
"pass@2": 0.0,
|
| 449 |
+
"pass@4": 0.0,
|
| 450 |
+
"pass@8": 0.0,
|
| 451 |
+
"pass@16": 0.0,
|
| 452 |
+
"pass@32": 0.0
|
| 453 |
+
},
|
| 454 |
+
"29": {
|
| 455 |
+
"pass@1": 0.0010416666666666667,
|
| 456 |
+
"pass@2": 0.0020833333333333333,
|
| 457 |
+
"pass@4": 0.004166666666666667,
|
| 458 |
+
"pass@8": 0.008333333333333333,
|
| 459 |
+
"pass@16": 0.016666666666666666,
|
| 460 |
+
"pass@32": 0.03333333333333333
|
| 461 |
+
},
|
| 462 |
+
"30": {
|
| 463 |
+
"pass@1": 0.000946969696969697,
|
| 464 |
+
"pass@2": 0.001893939393939394,
|
| 465 |
+
"pass@4": 0.003787878787878788,
|
| 466 |
+
"pass@8": 0.007575757575757576,
|
| 467 |
+
"pass@16": 0.015151515151515152,
|
| 468 |
+
"pass@32": 0.030303030303030304
|
| 469 |
+
}
|
| 470 |
+
}
|
| 471 |
+
}
|
| 472 |
+
}
|
| 473 |
+
},
|
| 474 |
+
"total": {
|
| 475 |
+
"answer_accuracy": 0.002484375,
|
| 476 |
+
"avg_loss": 0.0,
|
| 477 |
+
"count": 64000,
|
| 478 |
+
"validation_metrics": {
|
| 479 |
+
"id": {},
|
| 480 |
+
"ood": {}
|
| 481 |
+
},
|
| 482 |
+
"pass_at_k": {
|
| 483 |
+
"pass@1": 0.002484375,
|
| 484 |
+
"pass@2": 0.004610887096774193,
|
| 485 |
+
"pass@4": 0.008140781423804228,
|
| 486 |
+
"pass@8": 0.013616341851820162,
|
| 487 |
+
"pass@16": 0.022010931899641574,
|
| 488 |
+
"pass@32": 0.0355
|
| 489 |
+
},
|
| 490 |
+
"per_op_pass_at_k": {
|
| 491 |
+
"21": {
|
| 492 |
+
"pass@1": 0.0034375,
|
| 493 |
+
"pass@2": 0.00658266129032258,
|
| 494 |
+
"pass@4": 0.0120952447163515,
|
| 495 |
+
"pass@8": 0.020621523915461622,
|
| 496 |
+
"pass@16": 0.03146551724137931,
|
| 497 |
+
"pass@32": 0.045
|
| 498 |
+
},
|
| 499 |
+
"22": {
|
| 500 |
+
"pass@1": 0.00375,
|
| 501 |
+
"pass@2": 0.007298387096774193,
|
| 502 |
+
"pass@4": 0.013849972191323692,
|
| 503 |
+
"pass@8": 0.02514460511679644,
|
| 504 |
+
"pass@16": 0.0428642936596218,
|
| 505 |
+
"pass@32": 0.07
|
| 506 |
+
},
|
| 507 |
+
"23": {
|
| 508 |
+
"pass@1": 0.00328125,
|
| 509 |
+
"pass@2": 0.005756048387096774,
|
| 510 |
+
"pass@4": 0.009340100111234706,
|
| 511 |
+
"pass@8": 0.014399555061179087,
|
| 512 |
+
"pass@16": 0.02258063710080444,
|
| 513 |
+
"pass@32": 0.035
|
| 514 |
+
},
|
| 515 |
+
"24": {
|
| 516 |
+
"pass@1": 0.00375,
|
| 517 |
+
"pass@2": 0.007298387096774193,
|
| 518 |
+
"pass@4": 0.013872914349276975,
|
| 519 |
+
"pass@8": 0.025402515140279327,
|
| 520 |
+
"pass@16": 0.04447194413545916,
|
| 521 |
+
"pass@32": 0.075
|
| 522 |
+
},
|
| 523 |
+
"25": {
|
| 524 |
+
"pass@1": 0.004375,
|
| 525 |
+
"pass@2": 0.007600806451612902,
|
| 526 |
+
"pass@4": 0.011979838709677419,
|
| 527 |
+
"pass@8": 0.017230994552351615,
|
| 528 |
+
"pass@16": 0.024997952636584934,
|
| 529 |
+
"pass@32": 0.04
|
| 530 |
+
},
|
| 531 |
+
"26": {
|
| 532 |
+
"pass@1": 0.00203125,
|
| 533 |
+
"pass@2": 0.0035080645161290323,
|
| 534 |
+
"pass@4": 0.005417825361512791,
|
| 535 |
+
"pass@8": 0.007403268589030548,
|
| 536 |
+
"pass@16": 0.009999830729796393,
|
| 537 |
+
"pass@32": 0.015
|
| 538 |
+
},
|
| 539 |
+
"27": {
|
| 540 |
+
"pass@1": 0.0015625,
|
| 541 |
+
"pass@2": 0.002973790322580645,
|
| 542 |
+
"pass@4": 0.005421301446051168,
|
| 543 |
+
"pass@8": 0.009257353849956742,
|
| 544 |
+
"pass@16": 0.014955815103201089,
|
| 545 |
+
"pass@32": 0.025
|
| 546 |
+
},
|
| 547 |
+
"28": {
|
| 548 |
+
"pass@1": 0.00125,
|
| 549 |
+
"pass@2": 0.0022883064516129033,
|
| 550 |
+
"pass@4": 0.003866101223581757,
|
| 551 |
+
"pass@8": 0.00573586035766236,
|
| 552 |
+
"pass@16": 0.007483005808923495,
|
| 553 |
+
"pass@32": 0.01
|
| 554 |
+
},
|
| 555 |
+
"29": {
|
| 556 |
+
"pass@1": 0.0009375,
|
| 557 |
+
"pass@2": 0.0018649193548387095,
|
| 558 |
+
"pass@4": 0.0036895161290322583,
|
| 559 |
+
"pass@8": 0.0072177419354838715,
|
| 560 |
+
"pass@16": 0.01379032258064516,
|
| 561 |
+
"pass@32": 0.025
|
| 562 |
+
},
|
| 563 |
+
"30": {
|
| 564 |
+
"pass@1": 0.00046875,
|
| 565 |
+
"pass@2": 0.0009375,
|
| 566 |
+
"pass@4": 0.001875,
|
| 567 |
+
"pass@8": 0.00375,
|
| 568 |
+
"pass@16": 0.0075,
|
| 569 |
+
"pass@32": 0.015
|
| 570 |
+
}
|
| 571 |
+
},
|
| 572 |
+
"per_op_accuracy": {
|
| 573 |
+
"21": 0.0034375,
|
| 574 |
+
"22": 0.00375,
|
| 575 |
+
"23": 0.00328125,
|
| 576 |
+
"24": 0.00375,
|
| 577 |
+
"25": 0.004375,
|
| 578 |
+
"26": 0.00203125,
|
| 579 |
+
"27": 0.0015625,
|
| 580 |
+
"28": 0.00125,
|
| 581 |
+
"29": 0.0009375,
|
| 582 |
+
"30": 0.00046875
|
| 583 |
+
},
|
| 584 |
+
"per_op_avg_response_len": {
|
| 585 |
+
"21": 291.64796875,
|
| 586 |
+
"22": 295.7371875,
|
| 587 |
+
"23": 293.74296875,
|
| 588 |
+
"24": 300.16828125,
|
| 589 |
+
"25": 297.91453125,
|
| 590 |
+
"26": 304.6490625,
|
| 591 |
+
"27": 304.83328125,
|
| 592 |
+
"28": 294.66640625,
|
| 593 |
+
"29": 299.793125,
|
| 594 |
+
"30": 295.98703125
|
| 595 |
+
},
|
| 596 |
+
"per_op_avg_loss": {},
|
| 597 |
+
"per_op_length": {
|
| 598 |
+
"21": 291.64796875,
|
| 599 |
+
"22": 295.7371875,
|
| 600 |
+
"23": 293.74296875,
|
| 601 |
+
"24": 300.16828125,
|
| 602 |
+
"25": 297.91453125,
|
| 603 |
+
"26": 304.6490625,
|
| 604 |
+
"27": 304.83328125,
|
| 605 |
+
"28": 294.66640625,
|
| 606 |
+
"29": 299.793125,
|
| 607 |
+
"30": 295.98703125
|
| 608 |
+
},
|
| 609 |
+
"per_op_loss": {},
|
| 610 |
+
"per_template": {
|
| 611 |
+
"crazy_zootopia": {
|
| 612 |
+
"count": 23072,
|
| 613 |
+
"correct": 61,
|
| 614 |
+
"answer_accuracy": 0.0026438973647711513,
|
| 615 |
+
"avg_response_len": 276.247572815534,
|
| 616 |
+
"resp_tokens_sum": 6373584,
|
| 617 |
+
"pass_at_k": {
|
| 618 |
+
"pass@1": 0.0026438973647711513,
|
| 619 |
+
"pass@2": 0.004840387454700014,
|
| 620 |
+
"pass@4": 0.008337704553834667,
|
| 621 |
+
"pass@8": 0.013432497404332345,
|
| 622 |
+
"pass@16": 0.020918036351159127,
|
| 623 |
+
"pass@32": 0.033287101248266296
|
| 624 |
+
},
|
| 625 |
+
"per_op_pass_at_k": {
|
| 626 |
+
"21": {
|
| 627 |
+
"pass@1": 0.0011867088607594937,
|
| 628 |
+
"pass@2": 0.0023734177215189874,
|
| 629 |
+
"pass@4": 0.004746835443037975,
|
| 630 |
+
"pass@8": 0.00949367088607595,
|
| 631 |
+
"pass@16": 0.0189873417721519,
|
| 632 |
+
"pass@32": 0.0379746835443038
|
| 633 |
+
},
|
| 634 |
+
"22": {
|
| 635 |
+
"pass@1": 0.00390625,
|
| 636 |
+
"pass@2": 0.007560483870967741,
|
| 637 |
+
"pass@4": 0.014168520578420465,
|
| 638 |
+
"pass@8": 0.024950562353231984,
|
| 639 |
+
"pass@16": 0.03939562476826103,
|
| 640 |
+
"pass@32": 0.05555555555555555
|
| 641 |
+
},
|
| 642 |
+
"23": {
|
| 643 |
+
"pass@1": 0.0004734848484848485,
|
| 644 |
+
"pass@2": 0.000946969696969697,
|
| 645 |
+
"pass@4": 0.001893939393939394,
|
| 646 |
+
"pass@8": 0.003787878787878788,
|
| 647 |
+
"pass@16": 0.007575757575757576,
|
| 648 |
+
"pass@32": 0.015151515151515152
|
| 649 |
+
},
|
| 650 |
+
"24": {
|
| 651 |
+
"pass@1": 0.006161971830985915,
|
| 652 |
+
"pass@2": 0.011869604725124942,
|
| 653 |
+
"pass@4": 0.02214314809882655,
|
| 654 |
+
"pass@8": 0.03936646700124117,
|
| 655 |
+
"pass@16": 0.06689052868689084,
|
| 656 |
+
"pass@32": 0.11267605633802817
|
| 657 |
+
},
|
| 658 |
+
"25": {
|
| 659 |
+
"pass@1": 0.011408730158730158,
|
| 660 |
+
"pass@2": 0.019169226830517153,
|
| 661 |
+
"pass@4": 0.028110599078341014,
|
| 662 |
+
"pass@8": 0.0348603001661956,
|
| 663 |
+
"pass@16": 0.03967604011614265,
|
| 664 |
+
"pass@32": 0.047619047619047616
|
| 665 |
+
},
|
| 666 |
+
"26": {
|
| 667 |
+
"pass@1": 0.0,
|
| 668 |
+
"pass@2": 0.0,
|
| 669 |
+
"pass@4": 0.0,
|
| 670 |
+
"pass@8": 0.0,
|
| 671 |
+
"pass@16": 0.0,
|
| 672 |
+
"pass@32": 0.0
|
| 673 |
+
},
|
| 674 |
+
"27": {
|
| 675 |
+
"pass@1": 0.00043402777777777775,
|
| 676 |
+
"pass@2": 0.0008680555555555555,
|
| 677 |
+
"pass@4": 0.001736111111111111,
|
| 678 |
+
"pass@8": 0.003472222222222222,
|
| 679 |
+
"pass@16": 0.006944444444444444,
|
| 680 |
+
"pass@32": 0.013888888888888888
|
| 681 |
+
},
|
| 682 |
+
"28": {
|
| 683 |
+
"pass@1": 0.0028735632183908046,
|
| 684 |
+
"pass@2": 0.005260474601408972,
|
| 685 |
+
"pass@4": 0.008887589019728177,
|
| 686 |
+
"pass@8": 0.013185885879683586,
|
| 687 |
+
"pass@16": 0.017202312204421828,
|
| 688 |
+
"pass@32": 0.022988505747126436
|
| 689 |
+
},
|
| 690 |
+
"29": {
|
| 691 |
+
"pass@1": 0.0004166666666666667,
|
| 692 |
+
"pass@2": 0.0008333333333333334,
|
| 693 |
+
"pass@4": 0.0016666666666666668,
|
| 694 |
+
"pass@8": 0.0033333333333333335,
|
| 695 |
+
"pass@16": 0.006666666666666667,
|
| 696 |
+
"pass@32": 0.013333333333333334
|
| 697 |
+
},
|
| 698 |
+
"30": {
|
| 699 |
+
"pass@1": 0.0004464285714285714,
|
| 700 |
+
"pass@2": 0.0008928571428571428,
|
| 701 |
+
"pass@4": 0.0017857142857142857,
|
| 702 |
+
"pass@8": 0.0035714285714285713,
|
| 703 |
+
"pass@16": 0.007142857142857143,
|
| 704 |
+
"pass@32": 0.014285714285714285
|
| 705 |
+
}
|
| 706 |
+
}
|
| 707 |
+
},
|
| 708 |
+
"teachers_in_school": {
|
| 709 |
+
"count": 19936,
|
| 710 |
+
"correct": 29,
|
| 711 |
+
"answer_accuracy": 0.0014546548956661316,
|
| 712 |
+
"avg_response_len": 290.34595706260035,
|
| 713 |
+
"resp_tokens_sum": 5788337,
|
| 714 |
+
"pass_at_k": {
|
| 715 |
+
"pass@1": 0.0014546548956661316,
|
| 716 |
+
"pass@2": 0.0028607673587738823,
|
| 717 |
+
"pass@4": 0.005535087139803991,
|
| 718 |
+
"pass@8": 0.0103836615322536,
|
| 719 |
+
"pass@16": 0.018455498083299257,
|
| 720 |
+
"pass@32": 0.030497592295345103
|
| 721 |
+
},
|
| 722 |
+
"per_op_pass_at_k": {
|
| 723 |
+
"21": {
|
| 724 |
+
"pass@1": 0.004326923076923077,
|
| 725 |
+
"pass@2": 0.008374689826302729,
|
| 726 |
+
"pass@4": 0.015694361256096516,
|
| 727 |
+
"pass@8": 0.027637545991272352,
|
| 728 |
+
"pass@16": 0.0436382305125353,
|
| 729 |
+
"pass@32": 0.06153846153846154
|
| 730 |
+
},
|
| 731 |
+
"22": {
|
| 732 |
+
"pass@1": 0.0030737704918032786,
|
| 733 |
+
"pass@2": 0.006114489687995769,
|
| 734 |
+
"pass@4": 0.012096774193548387,
|
| 735 |
+
"pass@8": 0.023664727657324167,
|
| 736 |
+
"pass@16": 0.0452141723955579,
|
| 737 |
+
"pass@32": 0.08196721311475409
|
| 738 |
+
},
|
| 739 |
+
"23": {
|
| 740 |
+
"pass@1": 0.0013392857142857143,
|
| 741 |
+
"pass@2": 0.0026497695852534552,
|
| 742 |
+
"pass@4": 0.005184331797235023,
|
| 743 |
+
"pass@8": 0.00990783410138249,
|
| 744 |
+
"pass@16": 0.017972350230414748,
|
| 745 |
+
"pass@32": 0.02857142857142857
|
| 746 |
+
},
|
| 747 |
+
"24": {
|
| 748 |
+
"pass@1": 0.0027901785714285715,
|
| 749 |
+
"pass@2": 0.005472350230414745,
|
| 750 |
+
"pass@4": 0.010527073732718894,
|
| 751 |
+
"pass@8": 0.019498847926267278,
|
| 752 |
+
"pass@16": 0.03369815668202765,
|
| 753 |
+
"pass@32": 0.05357142857142857
|
| 754 |
+
},
|
| 755 |
+
"25": {
|
| 756 |
+
"pass@1": 0.0004280821917808219,
|
| 757 |
+
"pass@2": 0.0008561643835616438,
|
| 758 |
+
"pass@4": 0.0017123287671232876,
|
| 759 |
+
"pass@8": 0.003424657534246575,
|
| 760 |
+
"pass@16": 0.00684931506849315,
|
| 761 |
+
"pass@32": 0.0136986301369863
|
| 762 |
+
},
|
| 763 |
+
"26": {
|
| 764 |
+
"pass@1": 0.0006127450980392157,
|
| 765 |
+
"pass@2": 0.0012254901960784314,
|
| 766 |
+
"pass@4": 0.0024509803921568627,
|
| 767 |
+
"pass@8": 0.004901960784313725,
|
| 768 |
+
"pass@16": 0.00980392156862745,
|
| 769 |
+
"pass@32": 0.0196078431372549
|
| 770 |
+
},
|
| 771 |
+
"27": {
|
| 772 |
+
"pass@1": 0.0005387931034482759,
|
| 773 |
+
"pass@2": 0.0010775862068965517,
|
| 774 |
+
"pass@4": 0.0021551724137931034,
|
| 775 |
+
"pass@8": 0.004310344827586207,
|
| 776 |
+
"pass@16": 0.008620689655172414,
|
| 777 |
+
"pass@32": 0.017241379310344827
|
| 778 |
+
},
|
| 779 |
+
"28": {
|
| 780 |
+
"pass@1": 0.0,
|
| 781 |
+
"pass@2": 0.0,
|
| 782 |
+
"pass@4": 0.0,
|
| 783 |
+
"pass@8": 0.0,
|
| 784 |
+
"pass@16": 0.0,
|
| 785 |
+
"pass@32": 0.0
|
| 786 |
+
},
|
| 787 |
+
"29": {
|
| 788 |
+
"pass@1": 0.0014423076923076924,
|
| 789 |
+
"pass@2": 0.002853598014888337,
|
| 790 |
+
"pass@4": 0.005583126550868486,
|
| 791 |
+
"pass@8": 0.010669975186104219,
|
| 792 |
+
"pass@16": 0.01935483870967742,
|
| 793 |
+
"pass@32": 0.03076923076923077
|
| 794 |
+
},
|
| 795 |
+
"30": {
|
| 796 |
+
"pass@1": 0.0,
|
| 797 |
+
"pass@2": 0.0,
|
| 798 |
+
"pass@4": 0.0,
|
| 799 |
+
"pass@8": 0.0,
|
| 800 |
+
"pass@16": 0.0,
|
| 801 |
+
"pass@32": 0.0
|
| 802 |
+
}
|
| 803 |
+
}
|
| 804 |
+
},
|
| 805 |
+
"movie_festival_awards": {
|
| 806 |
+
"count": 20992,
|
| 807 |
+
"correct": 69,
|
| 808 |
+
"answer_accuracy": 0.003286966463414634,
|
| 809 |
+
"avg_response_len": 328.9145388719512,
|
| 810 |
+
"resp_tokens_sum": 6904574,
|
| 811 |
+
"pass_at_k": {
|
| 812 |
+
"pass@1": 0.003286966463414634,
|
| 813 |
+
"pass@2": 0.0060207267899291895,
|
| 814 |
+
"pass@4": 0.010398961244200873,
|
| 815 |
+
"pass@8": 0.016888463323967543,
|
| 816 |
+
"pass@16": 0.026588695555185955,
|
| 817 |
+
"pass@32": 0.042682926829268296
|
| 818 |
+
},
|
| 819 |
+
"per_op_pass_at_k": {
|
| 820 |
+
"21": {
|
| 821 |
+
"pass@1": 0.005580357142857143,
|
| 822 |
+
"pass@2": 0.010440668202764977,
|
| 823 |
+
"pass@4": 0.01828420467185762,
|
| 824 |
+
"pass@8": 0.028176148101064676,
|
| 825 |
+
"pass@16": 0.03493961544573335,
|
| 826 |
+
"pass@32": 0.03571428571428571
|
| 827 |
+
},
|
| 828 |
+
"22": {
|
| 829 |
+
"pass@1": 0.004197761194029851,
|
| 830 |
+
"pass@2": 0.008094607607125662,
|
| 831 |
+
"pass@4": 0.015103846728537512,
|
| 832 |
+
"pass@8": 0.026700479803430013,
|
| 833 |
+
"pass@16": 0.04445237660418707,
|
| 834 |
+
"pass@32": 0.07462686567164178
|
| 835 |
+
},
|
| 836 |
+
"23": {
|
| 837 |
+
"pass@1": 0.00830078125,
|
| 838 |
+
"pass@2": 0.014112903225806451,
|
| 839 |
+
"pass@4": 0.021564324944382644,
|
| 840 |
+
"pass@8": 0.030255666017797552,
|
| 841 |
+
"pass@16": 0.04309473287549774,
|
| 842 |
+
"pass@32": 0.0625
|
| 843 |
+
},
|
| 844 |
+
"24": {
|
| 845 |
+
"pass@1": 0.0021404109589041095,
|
| 846 |
+
"pass@2": 0.0042532037118868755,
|
| 847 |
+
"pass@4": 0.008395934600088379,
|
| 848 |
+
"pass@8": 0.016349977905435263,
|
| 849 |
+
"pass@16": 0.030932390631904547,
|
| 850 |
+
"pass@32": 0.0547945205479452
|
| 851 |
+
},
|
| 852 |
+
"25": {
|
| 853 |
+
"pass@1": 0.001953125,
|
| 854 |
+
"pass@2": 0.00390625,
|
| 855 |
+
"pass@4": 0.0078125,
|
| 856 |
+
"pass@8": 0.015625,
|
| 857 |
+
"pass@16": 0.03125,
|
| 858 |
+
"pass@32": 0.0625
|
| 859 |
+
},
|
| 860 |
+
"26": {
|
| 861 |
+
"pass@1": 0.004518072289156626,
|
| 862 |
+
"pass@2": 0.007700155460551886,
|
| 863 |
+
"pass@4": 0.01154897677472962,
|
| 864 |
+
"pass@8": 0.014827153226579631,
|
| 865 |
+
"pass@16": 0.018071881276617813,
|
| 866 |
+
"pass@32": 0.024096385542168676
|
| 867 |
+
},
|
| 868 |
+
"27": {
|
| 869 |
+
"pass@1": 0.0035714285714285713,
|
| 870 |
+
"pass@2": 0.0067108294930875575,
|
| 871 |
+
"pass@4": 0.011918004131574764,
|
| 872 |
+
"pass@8": 0.01930672528559069,
|
| 873 |
+
"pass@16": 0.028445186009145966,
|
| 874 |
+
"pass@32": 0.04285714285714286
|
| 875 |
+
},
|
| 876 |
+
"28": {
|
| 877 |
+
"pass@1": 0.0,
|
| 878 |
+
"pass@2": 0.0,
|
| 879 |
+
"pass@4": 0.0,
|
| 880 |
+
"pass@8": 0.0,
|
| 881 |
+
"pass@16": 0.0,
|
| 882 |
+
"pass@32": 0.0
|
| 883 |
+
},
|
| 884 |
+
"29": {
|
| 885 |
+
"pass@1": 0.0010416666666666667,
|
| 886 |
+
"pass@2": 0.0020833333333333333,
|
| 887 |
+
"pass@4": 0.004166666666666667,
|
| 888 |
+
"pass@8": 0.008333333333333333,
|
| 889 |
+
"pass@16": 0.016666666666666666,
|
| 890 |
+
"pass@32": 0.03333333333333333
|
| 891 |
+
},
|
| 892 |
+
"30": {
|
| 893 |
+
"pass@1": 0.000946969696969697,
|
| 894 |
+
"pass@2": 0.001893939393939394,
|
| 895 |
+
"pass@4": 0.003787878787878788,
|
| 896 |
+
"pass@8": 0.007575757575757576,
|
| 897 |
+
"pass@16": 0.015151515151515152,
|
| 898 |
+
"pass@32": 0.030303030303030304
|
| 899 |
+
}
|
| 900 |
+
}
|
| 901 |
+
}
|
| 902 |
+
}
|
| 903 |
+
}
|
| 904 |
+
}
|