developer_uid: rirv938
submission_id: rirv938-anthropic-grpo-_77402_v1
model_name: rirv938-anthropic-grpo-_77402_v1
model_group: rirv938/anthropic_grpo_4
status: torndown
timestamp: 2025-05-15T22:35:11+00:00
num_battles: 5919
num_wins: 3200
celo_rating: 1314.24
family_friendly_score: 0.5714
family_friendly_standard_error: 0.006998600431514861
submission_type: basic
model_repo: rirv938/anthropic_grpo_40k_cp546_95ff_baseline_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': 0.6358118190874026, 'latency_mean': 1.572705374956131, 'latency_p50': 1.5714366436004639, 'latency_p90': 1.7454931735992432}, {'batch_size': 3, 'throughput': 1.2237434764196282, 'latency_mean': 2.449652919769287, 'latency_p50': 2.456693649291992, 'latency_p90': 2.6859904289245606}, {'batch_size': 5, 'throughput': 1.5041774918997315, 'latency_mean': 3.3069571661949158, 'latency_p50': 3.2996857166290283, 'latency_p90': 3.7001095056533813}, {'batch_size': 6, 'throughput': 1.5742844906709217, 'latency_mean': 3.783701266050339, 'latency_p50': 3.7890785932540894, 'latency_p90': 4.263159584999085}, {'batch_size': 8, 'throughput': 1.6890574217462886, 'latency_mean': 4.703897720575332, 'latency_p50': 4.6973865032196045, 'latency_p90': 5.238753032684326}, {'batch_size': 10, 'throughput': 1.7439967082847163, 'latency_mean': 5.6773293793201445, 'latency_p50': 5.707589507102966, 'latency_p90': 6.462333416938781}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rirv938-anthropic-grpo-_77402_v1
is_internal_developer: True
language_model: rirv938/anthropic_grpo_40k_cp546_95ff_baseline_merged
model_size: 13B
ranking_group: single
throughput_3p7s: 1.57
us_pacific_date: 2025-05-15
win_ratio: 0.5406318634904544
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-77402-v1-mkmlizer
Waiting for job on rirv938-anthropic-grpo-77402-v1-mkmlizer to finish
Failed to get response for submission rirv938-anthropic-grpo-_72536_v1: ('http://rirv938-anthropic-grpo-72536-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:55052->127.0.0.1:8080: read: connection reset by peer\n')
rirv938-anthropic-grpo-77402-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-grpo-77402-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-anthropic-grpo-77402-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-anthropic-grpo-77402-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-anthropic-grpo-77402-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-anthropic-grpo-77402-v1-mkmlizer: ║       /___/                                                         ║
rirv938-anthropic-grpo-77402-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-77402-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-anthropic-grpo-77402-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-anthropic-grpo-77402-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-anthropic-grpo-77402-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-77402-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-anthropic-grpo-77402-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-anthropic-grpo-77402-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-77402-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-anthropic-grpo-77402-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-anthropic-grpo-77402-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-anthropic-grpo-77402-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-77402-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-anthropic-grpo-77402-v1-mkmlizer: Downloaded to shared memory in 79.219s
rirv938-anthropic-grpo-77402-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp2i9pew94, device:0
rirv938-anthropic-grpo-77402-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-77402-v1-mkmlizer: quantized model in 44.002s
rirv938-anthropic-grpo-77402-v1-mkmlizer: Processed model rirv938/anthropic_grpo_40k_cp546_95ff_baseline_merged in 123.222s
rirv938-anthropic-grpo-77402-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-77402-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-grpo-77402-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-grpo-77402-v1
rirv938-anthropic-grpo-77402-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-77402-v1/config.json
rirv938-anthropic-grpo-77402-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-77402-v1/special_tokens_map.json
rirv938-anthropic-grpo-77402-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-77402-v1/tokenizer_config.json
rirv938-anthropic-grpo-77402-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-77402-v1/tokenizer.json
rirv938-anthropic-grpo-77402-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-grpo-77402-v1/flywheel_model.0.safetensors
rirv938-anthropic-grpo-77402-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.51it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:13, 26.20it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:14, 23.38it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:11, 29.31it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:15, 21.40it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:17, 19.26it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:13, 24.97it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:12, 25.82it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:12, 26.39it/s]
Loading 0:  12%|█▏        | 42/363 [00:01<00:13, 23.50it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:11, 26.46it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:13, 23.25it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:11, 27.36it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:10, 27.58it/s]
Loading 0:  17%|█▋        | 63/363 [00:02<00:14, 20.14it/s]
Loading 0:  18%|█▊        | 66/363 [00:02<00:14, 20.71it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:13, 22.03it/s]
Loading 0:  20%|█▉        | 72/363 [00:03<00:14, 20.27it/s]
Loading 0:  21%|██        | 77/363 [00:03<00:13, 20.95it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:11, 25.27it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:12, 22.86it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:09, 27.31it/s]
Loading 0:  26%|██▌       | 95/363 [00:03<00:10, 24.77it/s]
Loading 0:  28%|██▊       | 100/363 [00:04<00:09, 29.02it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:13, 18.93it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:10, 23.26it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:11, 21.89it/s]
Loading 0:  33%|███▎      | 118/363 [00:04<00:09, 26.42it/s]
Loading 0:  34%|███▎      | 122/363 [00:05<00:09, 24.22it/s]
Loading 0:  35%|███▍      | 127/363 [00:05<00:08, 29.07it/s]
Loading 0:  36%|███▌      | 131/363 [00:05<00:09, 25.33it/s]
Loading 0:  37%|███▋      | 136/363 [00:05<00:07, 29.20it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:07, 29.87it/s]
Loading 0:  40%|███▉      | 145/363 [00:06<00:10, 21.14it/s]
Loading 0:  41%|████      | 149/363 [00:06<00:10, 20.51it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:08, 24.79it/s]
Loading 0:  44%|████▎     | 158/363 [00:06<00:08, 22.79it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:07, 27.24it/s]
Loading 0:  46%|████▌     | 167/363 [00:06<00:07, 24.82it/s]
Loading 0:  47%|████▋     | 172/363 [00:07<00:06, 28.68it/s]
Loading 0:  48%|████▊     | 176/363 [00:07<00:07, 25.43it/s]
Loading 0:  50%|████▉     | 181/363 [00:07<00:06, 29.66it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:09, 19.53it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 24.07it/s]
Loading 0:  53%|█████▎    | 194/363 [00:08<00:07, 22.37it/s]
Loading 0:  55%|█████▍    | 199/363 [00:08<00:06, 26.70it/s]
Loading 0:  56%|█████▌    | 203/363 [00:08<00:06, 24.28it/s]
Loading 0:  57%|█████▋    | 208/363 [00:08<00:05, 28.77it/s]
Loading 0:  58%|█████▊    | 212/363 [00:08<00:05, 25.48it/s]
Loading 0:  60%|█████▉    | 217/363 [00:08<00:04, 29.73it/s]
Loading 0:  61%|██████    | 222/363 [00:08<00:04, 29.60it/s]
Loading 0:  62%|██████▏   | 226/363 [00:09<00:06, 20.62it/s]
Loading 0:  63%|██████▎   | 230/363 [00:09<00:06, 19.62it/s]
Loading 0:  65%|██████▍   | 235/363 [00:09<00:05, 23.60it/s]
Loading 0:  66%|██████▌   | 239/363 [00:09<00:05, 21.90it/s]
Loading 0:  67%|██████▋   | 244/363 [00:10<00:04, 25.80it/s]
Loading 0:  68%|██████▊   | 248/363 [00:10<00:04, 23.64it/s]
Loading 0:  70%|██████▉   | 253/363 [00:10<00:03, 27.70it/s]
Loading 0:  71%|███████   | 257/363 [00:10<00:04, 24.10it/s]
Loading 0:  72%|███████▏  | 262/363 [00:10<00:03, 27.74it/s]
Loading 0:  73%|███████▎  | 266/363 [00:11<00:05, 18.40it/s]
Loading 0:  75%|███████▍  | 271/363 [00:11<00:04, 22.64it/s]
Loading 0:  76%|███████▌  | 275/363 [00:11<00:04, 21.52it/s]
Loading 0:  77%|███████▋  | 280/363 [00:11<00:03, 25.28it/s]
Loading 0:  78%|███████▊  | 284/363 [00:11<00:03, 23.00it/s]
Loading 0:  80%|████████  | 291/363 [00:11<00:02, 29.11it/s]
Loading 0:  81%|████████▏ | 295/363 [00:12<00:02, 28.16it/s]
Loading 0:  82%|████████▏ | 299/363 [00:12<00:02, 28.21it/s]
Loading 0:  84%|████████▎ | 304/363 [00:12<00:02, 24.60it/s]
Loading 0:  85%|████████▍ | 307/363 [00:12<00:02, 23.53it/s]
Loading 0:  86%|████████▌ | 311/363 [00:12<00:02, 22.69it/s]
Loading 0:  88%|████████▊ | 318/363 [00:12<00:01, 28.94it/s]
Loading 0:  89%|████████▊ | 322/363 [00:13<00:01, 27.68it/s]
Loading 0:  90%|█████████ | 327/363 [00:13<00:01, 29.43it/s]
Loading 0:  91%|█████████ | 331/363 [00:13<00:01, 28.22it/s]
Loading 0:  93%|█████████▎| 336/363 [00:13<00:00, 30.09it/s]
Loading 0:  94%|█████████▎| 340/363 [00:13<00:00, 28.76it/s]
Loading 0:  95%|█████████▍| 344/363 [00:20<00:09,  1.96it/s]
Loading 0:  96%|█████████▌| 348/363 [00:20<00:05,  2.64it/s]
Loading 0:  97%|█████████▋| 353/363 [00:21<00:02,  3.81it/s]
Loading 0:  98%|█████████▊| 357/363 [00:21<00:01,  4.94it/s]
Loading 0: 100%|█████████▉| 362/363 [00:21<00:00,  7.01it/s]
                                                            

Job rirv938-anthropic-grpo-77402-v1-mkmlizer completed after 155.63s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-77402-v1-mkmlizer
Pipeline stage MKMLizer completed in 156.12s
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 rirv938-anthropic-grpo-77402-v1
Waiting for inference service rirv938-anthropic-grpo-77402-v1 to be ready
Inference service rirv938-anthropic-grpo-77402-v1 ready after 130.5538351535797s
Pipeline stage MKMLDeployer completed in 131.33s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1575281620025635s
Received healthy response to inference request in 1.5550549030303955s
Received healthy response to inference request in 1.8878223896026611s
Received healthy response to inference request in 1.5243618488311768s
Received healthy response to inference request in 1.7393460273742676s
5 requests
0 failed requests
5th percentile: 1.5305004596710206
10th percentile: 1.5366390705108643
20th percentile: 1.5489162921905517
30th percentile: 1.5919131278991698
40th percentile: 1.6656295776367187
50th percentile: 1.7393460273742676
60th percentile: 1.798736572265625
70th percentile: 1.8581271171569824
80th percentile: 1.9417635440826417
90th percentile: 2.0496458530426027
95th percentile: 2.103587007522583
99th percentile: 2.1467399311065676
mean time: 1.772822666168213
Pipeline stage StressChecker completed in 10.31s
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 0.70s
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 0.76s
Shutdown handler de-registered
rirv938-anthropic-grpo-_77402_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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2510.64s
Shutdown handler de-registered
rirv938-anthropic-grpo-_77402_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-grpo-_77402_v1 status is now torndown due to DeploymentManager action