developer_uid: azuruce
submission_id: agentica-org-deepcoder-_75048_v1
model_name: nis-best-config
model_group: agentica-org/DeepCoder-1
status: torndown
timestamp: 2025-04-11T20:35:30+00:00
num_battles: 5680
num_wins: 2512
celo_rating: 1229.94
family_friendly_score: 0.6548
family_friendly_standard_error: 0.0067236442499585
submission_type: basic
model_repo: agentica-org/DeepCoder-14B-Preview
model_architecture: Qwen2ForCausalLM
model_num_parameters: 14769689600.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.46780866959971595, 'latency_mean': 2.137554208040237, 'latency_p50': 2.150662660598755, 'latency_p90': 2.369424033164978}, {'batch_size': 3, 'throughput': 0.8628505501492976, 'latency_mean': 3.461031259298325, 'latency_p50': 3.4583404064178467, 'latency_p90': 3.7876925468444824}, {'batch_size': 5, 'throughput': 1.0575779874959872, 'latency_mean': 4.716704778671264, 'latency_p50': 4.731098175048828, 'latency_p90': 5.3142753601074215}, {'batch_size': 6, 'throughput': 1.1054516839764474, 'latency_mean': 5.402745817899704, 'latency_p50': 5.416492342948914, 'latency_p90': 6.052905654907226}, {'batch_size': 10, 'throughput': 1.1891068251169632, 'latency_mean': 8.3240722489357, 'latency_p50': 8.278190016746521, 'latency_p90': 9.456470942497253}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: nis-best-config
ineligible_reason: num_battles<10000
is_internal_developer: False
language_model: agentica-org/DeepCoder-14B-Preview
model_size: 15B
ranking_group: single
throughput_3p7s: 0.91
us_pacific_date: 2025-04-11
win_ratio: 0.4422535211267606
generation_params: {'temperature': 0.45, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 40, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['\n', '<|im_end|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '<|system|>{memory}\n', 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{message}<|im_end|>\n', 'user_template': '<|im_start|>user\nYou:{message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n', 'truncate_by_message': False}
Resubmit model
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name agentica-org-deepcoder-75048-v1-mkmlizer
Waiting for job on agentica-org-deepcoder-75048-v1-mkmlizer to finish
agentica-org-deepcoder-75048-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
agentica-org-deepcoder-75048-v1-mkmlizer: ║ _____ __ __ ║
agentica-org-deepcoder-75048-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
agentica-org-deepcoder-75048-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
agentica-org-deepcoder-75048-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
agentica-org-deepcoder-75048-v1-mkmlizer: ║ /___/ ║
agentica-org-deepcoder-75048-v1-mkmlizer: ║ ║
agentica-org-deepcoder-75048-v1-mkmlizer: ║ Version: 0.12.8 ║
agentica-org-deepcoder-75048-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
agentica-org-deepcoder-75048-v1-mkmlizer: ║ https://mk1.ai ║
agentica-org-deepcoder-75048-v1-mkmlizer: ║ ║
agentica-org-deepcoder-75048-v1-mkmlizer: ║ The license key for the current software has been verified as ║
agentica-org-deepcoder-75048-v1-mkmlizer: ║ belonging to: ║
agentica-org-deepcoder-75048-v1-mkmlizer: ║ ║
agentica-org-deepcoder-75048-v1-mkmlizer: ║ Chai Research Corp. ║
agentica-org-deepcoder-75048-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
agentica-org-deepcoder-75048-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
agentica-org-deepcoder-75048-v1-mkmlizer: ║ ║
agentica-org-deepcoder-75048-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
agentica-org-deepcoder-75048-v1-mkmlizer: Downloaded to shared memory in 53.177s
agentica-org-deepcoder-75048-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpzjuixvs2, device:0
agentica-org-deepcoder-75048-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
agentica-org-deepcoder-75048-v1-mkmlizer: quantized model in 42.078s
agentica-org-deepcoder-75048-v1-mkmlizer: Processed model agentica-org/DeepCoder-14B-Preview in 95.271s
agentica-org-deepcoder-75048-v1-mkmlizer: creating bucket guanaco-mkml-models
agentica-org-deepcoder-75048-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
agentica-org-deepcoder-75048-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/agentica-org-deepcoder-75048-v1
agentica-org-deepcoder-75048-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/agentica-org-deepcoder-75048-v1/special_tokens_map.json
agentica-org-deepcoder-75048-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/agentica-org-deepcoder-75048-v1/config.json
agentica-org-deepcoder-75048-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/agentica-org-deepcoder-75048-v1/tokenizer_config.json
agentica-org-deepcoder-75048-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/agentica-org-deepcoder-75048-v1/tokenizer.json
agentica-org-deepcoder-75048-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/agentica-org-deepcoder-75048-v1/flywheel_model.1.safetensors
agentica-org-deepcoder-75048-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/agentica-org-deepcoder-75048-v1/flywheel_model.0.safetensors
agentica-org-deepcoder-75048-v1-mkmlizer: Loading 0: 0%| | 0/579 [00:00<?, ?it/s] Loading 0: 1%| | 5/579 [00:00<00:14, 39.71it/s] Loading 0: 3%|▎ | 19/579 [00:00<00:06, 88.37it/s] Loading 0: 5%|▌ | 29/579 [00:00<00:13, 40.99it/s] Loading 0: 7%|▋ | 40/579 [00:00<00:10, 53.73it/s] Loading 0: 9%|▉ | 51/579 [00:00<00:08, 64.08it/s] Loading 0: 10%|█ | 60/579 [00:00<00:07, 68.19it/s] Loading 0: 12%|█▏ | 69/579 [00:01<00:07, 67.21it/s] Loading 0: 13%|█▎ | 77/579 [00:01<00:09, 51.30it/s] Loading 0: 15%|█▍ | 85/579 [00:01<00:09, 52.98it/s] Loading 0: 17%|█▋ | 96/579 [00:01<00:07, 62.23it/s] Loading 0: 18%|█▊ | 107/579 [00:01<00:06, 70.43it/s] Loading 0: 20%|█▉ | 115/579 [00:01<00:06, 70.66it/s] Loading 0: 21%|██ | 123/579 [00:01<00:06, 69.21it/s] Loading 0: 23%|██▎ | 131/579 [00:02<00:08, 51.26it/s] Loading 0: 24%|██▎ | 137/579 [00:02<00:09, 47.47it/s] Loading 0: 26%|██▌ | 148/579 [00:02<00:07, 58.56it/s] Loading 0: 27%|██▋ | 159/579 [00:02<00:06, 67.68it/s] Loading 0: 29%|██▉ | 167/579 [00:02<00:06, 68.49it/s] Loading 0: 30%|███ | 175/579 [00:02<00:06, 67.26it/s] Loading 0: 32%|███▏ | 183/579 [00:03<00:07, 49.73it/s] Loading 0: 33%|███▎ | 191/579 [00:03<00:07, 54.25it/s] Loading 0: 34%|███▍ | 198/579 [00:03<00:06, 54.88it/s] Loading 0: 36%|███▌ | 208/579 [00:03<00:05, 63.10it/s] Loading 0: 38%|███▊ | 219/579 [00:03<00:05, 71.84it/s] Loading 0: 39%|███▉ | 227/579 [00:03<00:04, 71.75it/s] Loading 0: 41%|████ | 238/579 [00:03<00:05, 58.16it/s] Loading 0: 42%|████▏ | 245/579 [00:04<00:06, 50.13it/s] Loading 0: 44%|████▍ | 256/579 [00:04<00:05, 59.49it/s] Loading 0: 46%|████▌ | 267/579 [00:04<00:04, 67.81it/s] Loading 0: 47%|████▋ | 275/579 [00:04<00:04, 68.44it/s] Loading 0: 49%|████▉ | 283/579 [00:04<00:04, 67.46it/s] Loading 0: 50%|█████ | 291/579 [00:04<00:05, 50.35it/s] Loading 0: 52%|█████▏ | 299/579 [00:05<00:05, 54.93it/s] Loading 0: 53%|█████▎ | 306/579 [00:05<00:05, 54.13it/s] Loading 0: 55%|█████▍ | 316/579 [00:05<00:04, 62.02it/s] Loading 0: 56%|█████▋ | 327/579 [00:05<00:03, 70.65it/s] Loading 0: 58%|█████▊ | 335/579 [00:05<00:03, 70.85it/s] Loading 0: 60%|█████▉ | 346/579 [00:05<00:04, 56.39it/s] Loading 0: 61%|██████ | 353/579 [00:05<00:04, 48.84it/s] Loading 0: 63%|██████▎ | 364/579 [00:06<00:03, 58.86it/s] Loading 0: 65%|██████▍ | 375/579 [00:06<00:03, 67.21it/s] Loading 0: 66%|██████▌ | 383/579 [00:06<00:02, 68.24it/s] Loading 0: 68%|██████▊ | 391/579 [00:06<00:02, 67.50it/s] Loading 0: 69%|██████▉ | 399/579 [00:06<00:03, 51.11it/s] Loading 0: 70%|███████ | 407/579 [00:06<00:03, 55.40it/s] Loading 0: 72%|███████▏ | 414/579 [00:06<00:02, 55.92it/s] Loading 0: 73%|███████▎ | 424/579 [00:07<00:02, 63.99it/s] Loading 0: 75%|███████▌ | 435/579 [00:07<00:01, 72.35it/s] Loading 0: 77%|███████▋ | 443/579 [00:07<00:01, 71.77it/s] Loading 0: 78%|███████▊ | 454/579 [00:07<00:02, 56.24it/s] Loading 0: 80%|███████▉ | 461/579 [00:07<00:02, 47.60it/s] Loading 0: 82%|████████▏ | 472/579 [00:07<00:01, 56.66it/s] Loading 0: 83%|████████▎ | 483/579 [00:08<00:01, 63.67it/s] Loading 0: 85%|████████▍ | 491/579 [00:08<00:01, 63.70it/s] Loading 0: 86%|████████▌ | 498/579 [00:08<00:01, 60.46it/s] Loading 0: 87%|████████▋ | 506/579 [00:08<00:01, 48.79it/s] Loading 0: 88%|████████▊ | 512/579 [00:08<00:01, 48.14it/s] Loading 0: 90%|████████▉ | 520/579 [00:08<00:01, 53.39it/s] Loading 0: 92%|█████████▏| 531/579 [00:08<00:00, 63.87it/s] Loading 0: 92%|█████████▏| 531/579 [00:23<00:00, 63.87it/s] Loading 0: 92%|█████████▏| 532/579 [00:23<00:33, 1.41it/s] Loading 0: 94%|█████████▍| 543/579 [00:23<00:14, 2.41it/s] Loading 0: 95%|█████████▌| 551/579 [00:24<00:08, 3.42it/s] Loading 0: 97%|█████████▋| 562/579 [00:32<00:07, 2.18it/s] Loading 0: 98%|█████████▊| 568/579 [00:32<00:03, 2.78it/s] Loading 0: 99%|█████████▉| 576/579 [00:32<00:00, 3.91it/s]
Job agentica-org-deepcoder-75048-v1-mkmlizer completed after 115.08s with status: succeeded
Stopping job with name agentica-org-deepcoder-75048-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.58s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service agentica-org-deepcoder-75048-v1
Waiting for inference service agentica-org-deepcoder-75048-v1 to be ready
Inference service agentica-org-deepcoder-75048-v1 ready after 110.37316727638245s
Pipeline stage MKMLDeployer completed in 110.87s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6932148933410645s
Received healthy response to inference request in 1.958719253540039s
Received healthy response to inference request in 2.235969305038452s
Received healthy response to inference request in 2.2031943798065186s
Received healthy response to inference request in 2.021136999130249s
5 requests
0 failed requests
5th percentile: 1.971202802658081
10th percentile: 1.983686351776123
20th percentile: 2.008653450012207
30th percentile: 2.057548475265503
40th percentile: 2.130371427536011
50th percentile: 2.2031943798065186
60th percentile: 2.216304349899292
70th percentile: 2.2294143199920655
80th percentile: 2.3274184226989747
90th percentile: 2.5103166580200194
95th percentile: 2.601765775680542
99th percentile: 2.67492506980896
mean time: 2.2224469661712645
Pipeline stage StressChecker completed in 12.45s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 0.64s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.59s
Shutdown handler de-registered
agentica-org-deepcoder-_75048_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service agentica-org-deepcoder-75048-v1-profiler
Waiting for inference service agentica-org-deepcoder-75048-v1-profiler to be ready
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 2861.17s
Shutdown handler de-registered
agentica-org-deepcoder-_75048_v1 status is now inactive due to auto deactivation removed underperforming models
agentica-org-deepcoder-_75048_v1 status is now torndown due to DeploymentManager action