developer_uid: rirv938
submission_id: rirv938-anthropic-grpo-_49826_v1
model_name: rirv938-anthropic-grpo-_49826_v1
model_group: rirv938/anthropic_grpo_4
status: torndown
timestamp: 2025-05-17T17:37:18+00:00
num_battles: 10252
num_wins: 5448
celo_rating: 1306.81
family_friendly_score: 0.5444
family_friendly_standard_error: 0.0070431333935969155
submission_type: basic
model_repo: rirv938/anthropic_grpo_40k_cp1184_95ff_beta6_3_merged
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': 0.6432555783577271, 'latency_mean': 1.5544976377487183, 'latency_p50': 1.5784635543823242, 'latency_p90': 1.7245113372802734}, {'batch_size': 3, 'throughput': 1.236141173229095, 'latency_mean': 2.4204206240177153, 'latency_p50': 2.433618426322937, 'latency_p90': 2.6456770658493043}, {'batch_size': 5, 'throughput': 1.5513988149681248, 'latency_mean': 3.2048243629932402, 'latency_p50': 3.2000938653945923, 'latency_p90': 3.640259599685669}, {'batch_size': 6, 'throughput': 1.6225029505924744, 'latency_mean': 3.678756138086319, 'latency_p50': 3.6985299587249756, 'latency_p90': 4.122138953208923}, {'batch_size': 8, 'throughput': 1.7199444827070867, 'latency_mean': 4.615253449678421, 'latency_p50': 4.584481120109558, 'latency_p90': 5.171273827552795}, {'batch_size': 10, 'throughput': 1.7617810320302496, 'latency_mean': 5.624222935438156, 'latency_p50': 5.639788031578064, 'latency_p90': 6.333493137359619}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rirv938-anthropic-grpo-_49826_v1
is_internal_developer: True
language_model: rirv938/anthropic_grpo_40k_cp1184_95ff_beta6_3_merged
model_size: 13B
ranking_group: single
throughput_3p7s: 1.63
us_pacific_date: 2025-05-17
win_ratio: 0.5314085056574327
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 rirv938-anthropic-grpo-49826-v1-mkmlizer
Waiting for job on rirv938-anthropic-grpo-49826-v1-mkmlizer to finish
rirv938-anthropic-grpo-49826-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-grpo-49826-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-anthropic-grpo-49826-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-anthropic-grpo-49826-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-anthropic-grpo-49826-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-anthropic-grpo-49826-v1-mkmlizer: ║       /___/                                                         ║
rirv938-anthropic-grpo-49826-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-49826-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-anthropic-grpo-49826-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-anthropic-grpo-49826-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-anthropic-grpo-49826-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-49826-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-anthropic-grpo-49826-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-anthropic-grpo-49826-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-49826-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-anthropic-grpo-49826-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-anthropic-grpo-49826-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-anthropic-grpo-49826-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-49826-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-anthropic-grpo-49826-v1-mkmlizer: Downloaded to shared memory in 76.197s
rirv938-anthropic-grpo-49826-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpxx2ciy15, device:0
rirv938-anthropic-grpo-49826-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-49826-v1-mkmlizer: quantized model in 43.430s
rirv938-anthropic-grpo-49826-v1-mkmlizer: Processed model rirv938/anthropic_grpo_40k_cp1184_95ff_beta6_3_merged in 119.627s
rirv938-anthropic-grpo-49826-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-49826-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-grpo-49826-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-grpo-49826-v1
rirv938-anthropic-grpo-49826-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-49826-v1/config.json
rirv938-anthropic-grpo-49826-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-49826-v1/special_tokens_map.json
rirv938-anthropic-grpo-49826-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-49826-v1/tokenizer_config.json
rirv938-anthropic-grpo-49826-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-49826-v1/tokenizer.json
rirv938-anthropic-grpo-49826-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-grpo-49826-v1/flywheel_model.0.safetensors
rirv938-anthropic-grpo-49826-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:17, 20.89it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:13, 26.20it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:15, 22.89it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:12, 28.48it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:17, 19.77it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:18, 18.20it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:13, 23.75it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:13, 23.95it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:11, 27.12it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:12, 26.38it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 28.76it/s]
Loading 0:  14%|█▍        | 52/363 [00:02<00:11, 27.75it/s]
Loading 0:  15%|█▌        | 56/363 [00:02<00:10, 28.42it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:12, 24.66it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:14, 21.20it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:11, 26.36it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:11, 25.37it/s]
Loading 0:  21%|██        | 77/363 [00:03<00:12, 22.90it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:10, 27.44it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:11, 24.66it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:08, 30.77it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:09, 29.28it/s]
Loading 0:  28%|██▊       | 101/363 [00:04<00:11, 23.53it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:13, 19.92it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:10, 24.71it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:10, 23.45it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:07, 30.65it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 29.48it/s]
Loading 0:  36%|███▌      | 129/363 [00:05<00:07, 31.85it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:07, 30.73it/s]
Loading 0:  38%|███▊      | 137/363 [00:05<00:07, 31.01it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 26.38it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:09, 23.80it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:09, 22.17it/s]
Loading 0:  43%|████▎     | 156/363 [00:06<00:07, 28.52it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:07, 27.77it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:06, 29.60it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:07, 27.56it/s]
Loading 0:  47%|████▋     | 172/363 [00:06<00:06, 28.04it/s]
Loading 0:  48%|████▊     | 176/363 [00:06<00:07, 24.33it/s]
Loading 0:  50%|████▉     | 181/363 [00:06<00:06, 29.39it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:09, 19.30it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 24.01it/s]
Loading 0:  53%|█████▎    | 194/363 [00:07<00:07, 22.26it/s]
Loading 0:  55%|█████▍    | 199/363 [00:07<00:06, 26.89it/s]
Loading 0:  56%|█████▌    | 203/363 [00:07<00:06, 24.08it/s]
Loading 0:  57%|█████▋    | 208/363 [00:08<00:05, 28.60it/s]
Loading 0:  58%|█████▊    | 212/363 [00:08<00:06, 25.14it/s]
Loading 0:  60%|█████▉    | 217/363 [00:08<00:04, 29.65it/s]
Loading 0:  61%|██████    | 222/363 [00:08<00:04, 30.46it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:06, 21.08it/s]
Loading 0:  63%|██████▎   | 230/363 [00:09<00:06, 19.59it/s]
Loading 0:  65%|██████▍   | 235/363 [00:09<00:05, 23.95it/s]
Loading 0:  66%|██████▌   | 239/363 [00:09<00:05, 21.99it/s]
Loading 0:  67%|██████▋   | 244/363 [00:09<00:04, 26.35it/s]
Loading 0:  68%|██████▊   | 248/363 [00:09<00:04, 23.35it/s]
Loading 0:  70%|██████▉   | 253/363 [00:09<00:04, 27.17it/s]
Loading 0:  71%|███████   | 257/363 [00:10<00:04, 24.09it/s]
Loading 0:  72%|███████▏  | 262/363 [00:10<00:03, 28.21it/s]
Loading 0:  73%|███████▎  | 266/363 [00:10<00:05, 18.87it/s]
Loading 0:  75%|███████▍  | 271/363 [00:10<00:03, 23.22it/s]
Loading 0:  76%|███████▌  | 275/363 [00:10<00:04, 21.67it/s]
Loading 0:  77%|███████▋  | 280/363 [00:11<00:03, 26.19it/s]
Loading 0:  78%|███████▊  | 284/363 [00:11<00:03, 23.52it/s]
Loading 0:  80%|███████▉  | 289/363 [00:11<00:02, 27.81it/s]
Loading 0:  81%|████████  | 293/363 [00:11<00:02, 23.93it/s]
Loading 0:  82%|████████▏ | 298/363 [00:11<00:02, 28.29it/s]
Loading 0:  83%|████████▎ | 303/363 [00:11<00:02, 28.99it/s]
Loading 0:  85%|████████▍ | 307/363 [00:12<00:02, 20.44it/s]
Loading 0:  86%|████████▌ | 311/363 [00:12<00:02, 19.69it/s]
Loading 0:  87%|████████▋ | 316/363 [00:12<00:01, 23.85it/s]
Loading 0:  88%|████████▊ | 319/363 [00:12<00:01, 24.91it/s]
Loading 0:  89%|████████▊ | 322/363 [00:12<00:01, 24.33it/s]
Loading 0:  90%|████████▉ | 325/363 [00:12<00:01, 25.26it/s]
Loading 0:  91%|█████████ | 329/363 [00:13<00:01, 21.86it/s]
Loading 0:  92%|█████████▏| 334/363 [00:13<00:01, 26.20it/s]
Loading 0:  93%|█████████▎| 338/363 [00:13<00:01, 22.88it/s]
Loading 0:  94%|█████████▍| 343/363 [00:13<00:00, 27.53it/s]
Loading 0:  96%|█████████▌| 347/363 [00:20<00:08,  1.88it/s]
Loading 0:  96%|█████████▋| 350/363 [00:20<00:05,  2.38it/s]
Loading 0:  97%|█████████▋| 353/363 [00:21<00:03,  3.03it/s]
Loading 0:  98%|█████████▊| 357/363 [00:21<00:01,  4.17it/s]
Loading 0: 100%|█████████▉| 362/363 [00:21<00:00,  6.25it/s]
                                                            

Job rirv938-anthropic-grpo-49826-v1-mkmlizer completed after 145.2s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-49826-v1-mkmlizer
Pipeline stage MKMLizer completed in 145.72s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-anthropic-grpo-49826-v1
Waiting for inference service rirv938-anthropic-grpo-49826-v1 to be ready
Inference service rirv938-anthropic-grpo-49826-v1 ready after 140.69713878631592s
Pipeline stage MKMLDeployer completed in 141.13s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.467017650604248s
Received healthy response to inference request in 2.0405666828155518s
Received healthy response to inference request in 1.8763480186462402s
Received healthy response to inference request in 1.5160503387451172s
Received healthy response to inference request in 1.678271770477295s
5 requests
0 failed requests
5th percentile: 1.5484946250915528
10th percentile: 1.5809389114379884
20th percentile: 1.6458274841308593
30th percentile: 1.717887020111084
40th percentile: 1.7971175193786622
50th percentile: 1.8763480186462402
60th percentile: 1.9420354843139649
70th percentile: 2.0077229499816895
80th percentile: 2.125856876373291
90th percentile: 2.2964372634887695
95th percentile: 2.381727457046509
99th percentile: 2.4499596118927003
mean time: 1.9156508922576905
Pipeline stage StressChecker completed in 10.79s
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 0.69s
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 0.62s
Shutdown handler de-registered
rirv938-anthropic-grpo-_49826_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4767.63s
Shutdown handler de-registered
rirv938-anthropic-grpo-_49826_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-grpo-_49826_v1 status is now torndown due to DeploymentManager action