developer_uid: rirv938
submission_id: chaiml-anthropic-grpo-4_66492_v3
model_name: chaiml-anthropic-grpo-4_66492_v3
model_group: ChaiML/anthropic_grpo_40
status: torndown
timestamp: 2025-05-01T18:50:00+00:00
num_battles: 6925
num_wins: 3649
celo_rating: 1326.03
family_friendly_score: 0.5631999999999999
family_friendly_standard_error: 0.007014353284515972
submission_type: basic
model_repo: ChaiML/anthropic_grpo_40k_cp1184_95ff
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 768
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.6336126405557432, 'latency_mean': 1.5781847727298737, 'latency_p50': 1.5733062028884888, 'latency_p90': 1.7331296443939208}, {'batch_size': 3, 'throughput': 1.228050199199885, 'latency_mean': 2.4386019575595856, 'latency_p50': 2.4657726287841797, 'latency_p90': 2.709929585456848}, {'batch_size': 5, 'throughput': 1.4944570919733404, 'latency_mean': 3.324524017572403, 'latency_p50': 3.3324536085128784, 'latency_p90': 3.695228385925293}, {'batch_size': 6, 'throughput': 1.5936444745378502, 'latency_mean': 3.7322883200645447, 'latency_p50': 3.7199496030807495, 'latency_p90': 4.268655848503113}, {'batch_size': 8, 'throughput': 1.6763060266127665, 'latency_mean': 4.730363467931747, 'latency_p50': 4.725696086883545, 'latency_p90': 5.2757751703262326}, {'batch_size': 10, 'throughput': 1.727032509199405, 'latency_mean': 5.743723212480545, 'latency_p50': 5.746154069900513, 'latency_p90': 6.464705109596252}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-anthropic-grpo-4_66492_v3
is_internal_developer: True
language_model: ChaiML/anthropic_grpo_40k_cp1184_95ff
model_size: 13B
ranking_group: single
throughput_3p7s: 1.6
us_pacific_date: 2025-05-01
win_ratio: 0.5269314079422383
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['You:', '</s>', '\n', '###'], 'max_input_tokens': 768, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', '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 chaiml-anthropic-grpo-4-66492-v3-mkmlizer
Waiting for job on chaiml-anthropic-grpo-4-66492-v3-mkmlizer to finish
chaiml-anthropic-grpo-4-66492-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-anthropic-grpo-4-66492-v3-mkmlizer: ║     _____            __           __                                ║
chaiml-anthropic-grpo-4-66492-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-anthropic-grpo-4-66492-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-anthropic-grpo-4-66492-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-anthropic-grpo-4-66492-v3-mkmlizer: ║       /___/                                                         ║
chaiml-anthropic-grpo-4-66492-v3-mkmlizer: ║                                                                     ║
chaiml-anthropic-grpo-4-66492-v3-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-anthropic-grpo-4-66492-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-anthropic-grpo-4-66492-v3-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-anthropic-grpo-4-66492-v3-mkmlizer: ║                                                                     ║
chaiml-anthropic-grpo-4-66492-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-anthropic-grpo-4-66492-v3-mkmlizer: ║  belonging to:                                                      ║
chaiml-anthropic-grpo-4-66492-v3-mkmlizer: ║                                                                     ║
chaiml-anthropic-grpo-4-66492-v3-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-anthropic-grpo-4-66492-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-anthropic-grpo-4-66492-v3-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-anthropic-grpo-4-66492-v3-mkmlizer: ║                                                                     ║
chaiml-anthropic-grpo-4-66492-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission chaiml-anthropic-grpo-4_66492_v1: HTTPConnectionPool(host='chaiml-anthropic-grpo-4-66492-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-anthropic-grpo-4-66492-v3-mkmlizer: Downloaded to shared memory in 64.720s
chaiml-anthropic-grpo-4-66492-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp7nw_t9sk, device:0
chaiml-anthropic-grpo-4-66492-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-anthropic-grpo-4-66492-v3-mkmlizer: quantized model in 43.149s
chaiml-anthropic-grpo-4-66492-v3-mkmlizer: Processed model ChaiML/anthropic_grpo_40k_cp1184_95ff in 107.870s
chaiml-anthropic-grpo-4-66492-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-anthropic-grpo-4-66492-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-anthropic-grpo-4-66492-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-anthropic-grpo-4-66492-v3
chaiml-anthropic-grpo-4-66492-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-anthropic-grpo-4-66492-v3/config.json
chaiml-anthropic-grpo-4-66492-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-anthropic-grpo-4-66492-v3/special_tokens_map.json
chaiml-anthropic-grpo-4-66492-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-anthropic-grpo-4-66492-v3/tokenizer_config.json
chaiml-anthropic-grpo-4-66492-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-anthropic-grpo-4-66492-v3/tokenizer.json
chaiml-anthropic-grpo-4-66492-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-anthropic-grpo-4-66492-v3/flywheel_model.0.safetensors
chaiml-anthropic-grpo-4-66492-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:17, 20.04it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:14, 24.96it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:15, 22.08it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:12, 27.50it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:17, 19.86it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:19, 17.72it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:14, 23.16it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:14, 22.87it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:13, 23.74it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:15, 21.40it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:12, 25.97it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:13, 23.43it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:10, 28.35it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:10, 29.72it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:14, 20.00it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:11, 26.29it/s]
Loading 0:  21%|██        | 75/363 [00:03<00:11, 26.13it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:11, 25.03it/s]
Loading 0:  23%|██▎       | 84/363 [00:03<00:10, 27.75it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:10, 27.09it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:09, 29.01it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:09, 28.04it/s]
Loading 0:  28%|██▊       | 101/363 [00:04<00:11, 22.31it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:13, 19.67it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:10, 24.58it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:11, 22.04it/s]
Loading 0:  33%|███▎      | 118/363 [00:04<00:09, 26.66it/s]
Loading 0:  34%|███▎      | 122/363 [00:05<00:09, 24.15it/s]
Loading 0:  35%|███▍      | 127/363 [00:05<00:08, 28.46it/s]
Loading 0:  36%|███▌      | 131/363 [00:05<00:09, 24.84it/s]
Loading 0:  37%|███▋      | 136/363 [00:05<00:07, 28.79it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:07, 29.32it/s]
Loading 0:  40%|███▉      | 145/363 [00:06<00:10, 20.90it/s]
Loading 0:  41%|████      | 149/363 [00:06<00:10, 20.19it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:08, 24.26it/s]
Loading 0:  44%|████▎     | 158/363 [00:06<00:09, 21.95it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:07, 25.75it/s]
Loading 0:  46%|████▌     | 167/363 [00:06<00:08, 23.11it/s]
Loading 0:  47%|████▋     | 172/363 [00:07<00:07, 27.18it/s]
Loading 0:  48%|████▊     | 176/363 [00:07<00:07, 24.03it/s]
Loading 0:  50%|████▉     | 181/363 [00:07<00:06, 27.90it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:09, 18.82it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 22.96it/s]
Loading 0:  53%|█████▎    | 194/363 [00:08<00:07, 21.72it/s]
Loading 0:  55%|█████▍    | 199/363 [00:08<00:06, 26.17it/s]
Loading 0:  56%|█████▌    | 203/363 [00:08<00:06, 24.18it/s]
Loading 0:  58%|█████▊    | 210/363 [00:08<00:05, 30.31it/s]
Loading 0:  59%|█████▉    | 214/363 [00:08<00:05, 28.71it/s]
Loading 0:  60%|██████    | 218/363 [00:08<00:05, 28.89it/s]
Loading 0:  61%|██████▏   | 223/363 [00:09<00:05, 25.22it/s]
Loading 0:  62%|██████▏   | 226/363 [00:09<00:05, 23.82it/s]
Loading 0:  63%|██████▎   | 230/363 [00:09<00:05, 23.00it/s]
Loading 0:  65%|██████▌   | 237/363 [00:09<00:04, 29.06it/s]
Loading 0:  66%|██████▋   | 241/363 [00:09<00:04, 28.14it/s]
Loading 0:  68%|██████▊   | 246/363 [00:09<00:03, 30.24it/s]
Loading 0:  69%|██████▉   | 250/363 [00:10<00:04, 28.09it/s]
Loading 0:  70%|██████▉   | 253/363 [00:10<00:03, 28.11it/s]
Loading 0:  71%|███████   | 257/363 [00:10<00:04, 24.70it/s]
Loading 0:  72%|███████▏  | 262/363 [00:10<00:03, 29.32it/s]
Loading 0:  73%|███████▎  | 266/363 [00:10<00:05, 19.06it/s]
Loading 0:  75%|███████▍  | 271/363 [00:10<00:03, 23.72it/s]
Loading 0:  76%|███████▌  | 275/363 [00:11<00:04, 21.93it/s]
Loading 0:  77%|███████▋  | 280/363 [00:11<00:03, 26.09it/s]
Loading 0:  78%|███████▊  | 284/363 [00:11<00:03, 23.39it/s]
Loading 0:  80%|███████▉  | 289/363 [00:11<00:02, 27.54it/s]
Loading 0:  81%|████████  | 293/363 [00:11<00:02, 24.03it/s]
Loading 0:  82%|████████▏ | 298/363 [00:12<00:02, 28.05it/s]
Loading 0:  83%|████████▎ | 303/363 [00:12<00:02, 28.93it/s]
Loading 0:  85%|████████▍ | 307/363 [00:12<00:02, 19.72it/s]
Loading 0:  86%|████████▌ | 311/363 [00:12<00:02, 19.29it/s]
Loading 0:  87%|████████▋ | 316/363 [00:12<00:02, 23.25it/s]
Loading 0:  88%|████████▊ | 320/363 [00:13<00:01, 21.76it/s]
Loading 0:  90%|████████▉ | 325/363 [00:13<00:01, 25.74it/s]
Loading 0:  91%|█████████ | 329/363 [00:13<00:01, 23.15it/s]
Loading 0:  92%|█████████▏| 334/363 [00:13<00:01, 26.87it/s]
Loading 0:  93%|█████████▎| 338/363 [00:13<00:01, 23.58it/s]
Loading 0:  94%|█████████▍| 343/363 [00:13<00:00, 27.34it/s]
Loading 0:  96%|█████████▌| 347/363 [00:20<00:08,  1.98it/s]
Loading 0:  96%|█████████▋| 350/363 [00:21<00:05,  2.50it/s]
Loading 0:  97%|█████████▋| 353/363 [00:21<00:03,  3.19it/s]
Loading 0:  98%|█████████▊| 357/363 [00:21<00:01,  4.38it/s]
Loading 0: 100%|█████████▉| 362/363 [00:21<00:00,  6.52it/s]
                                                            

Job chaiml-anthropic-grpo-4-66492-v3-mkmlizer completed after 145.27s with status: succeeded
Stopping job with name chaiml-anthropic-grpo-4-66492-v3-mkmlizer
Pipeline stage MKMLizer completed in 145.74s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-anthropic-grpo-4-66492-v3
Waiting for inference service chaiml-anthropic-grpo-4-66492-v3 to be ready
Inference service chaiml-anthropic-grpo-4-66492-v3 ready after 140.5293366909027s
Pipeline stage MKMLDeployer completed in 140.97s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.336132049560547s
Received healthy response to inference request in 1.758474588394165s
Received healthy response to inference request in 1.895143985748291s
Received healthy response to inference request in 1.8211421966552734s
Received healthy response to inference request in 1.9257869720458984s
5 requests
0 failed requests
5th percentile: 1.7710081100463868
10th percentile: 1.7835416316986084
20th percentile: 1.8086086750030517
30th percentile: 1.835942554473877
40th percentile: 1.865543270111084
50th percentile: 1.895143985748291
60th percentile: 1.907401180267334
70th percentile: 1.919658374786377
80th percentile: 2.007855987548828
90th percentile: 2.1719940185546873
95th percentile: 2.254063034057617
99th percentile: 2.319718246459961
mean time: 1.947335958480835
Pipeline stage StressChecker completed in 11.26s
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 0.73s
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 0.87s
Shutdown handler de-registered
chaiml-anthropic-grpo-4_66492_v3 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 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-anthropic-grpo-4-66492-v3-profiler
Waiting for inference service chaiml-anthropic-grpo-4-66492-v3-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 2737.18s
Shutdown handler de-registered
chaiml-anthropic-grpo-4_66492_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-anthropic-grpo-4_66492_v3 status is now torndown due to DeploymentManager action