developer_uid: rirv938
submission_id: rirv938-anthropic-grpo-_73855_v1
model_name: rirv938-anthropic-grpo-_73855_v1
model_group: rirv938/anthropic_grpo_4
status: torndown
timestamp: 2025-04-30T02:49:37+00:00
num_battles: 5582
num_wins: 3089
celo_rating: 1329.24
family_friendly_score: 0.5298
family_friendly_standard_error: 0.007058497857193129
submission_type: basic
model_repo: rirv938/anthropic_grpo_40k_cp1184_99ff_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': 0.6421608743798534, 'latency_mean': 1.5571482026576995, 'latency_p50': 1.5670185089111328, 'latency_p90': 1.723798131942749}, {'batch_size': 3, 'throughput': 1.2272516452725184, 'latency_mean': 2.4366315317153933, 'latency_p50': 2.4455424547195435, 'latency_p90': 2.699185824394226}, {'batch_size': 5, 'throughput': 1.5103288155683277, 'latency_mean': 3.3065268325805666, 'latency_p50': 3.3098790645599365, 'latency_p90': 3.6745059728622436}, {'batch_size': 6, 'throughput': 1.5971774398602845, 'latency_mean': 3.73797887802124, 'latency_p50': 3.777371048927307, 'latency_p90': 4.131000971794128}, {'batch_size': 8, 'throughput': 1.6652456627569083, 'latency_mean': 4.778374229669571, 'latency_p50': 4.774463415145874, 'latency_p90': 5.363124871253968}, {'batch_size': 10, 'throughput': 1.7343459128391012, 'latency_mean': 5.726128073930741, 'latency_p50': 5.712231755256653, 'latency_p90': 6.411096310615539}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rirv938-anthropic-grpo-_73855_v1
is_internal_developer: True
language_model: rirv938/anthropic_grpo_40k_cp1184_99ff_merged
model_size: 13B
ranking_group: single
throughput_3p7s: 1.6
us_pacific_date: 2025-04-29
win_ratio: 0.5533858831959871
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-73855-v1-mkmlizer
Waiting for job on rirv938-anthropic-grpo-73855-v1-mkmlizer to finish
rirv938-anthropic-grpo-73855-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-grpo-73855-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-anthropic-grpo-73855-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-anthropic-grpo-73855-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-anthropic-grpo-73855-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-anthropic-grpo-73855-v1-mkmlizer: ║       /___/                                                         ║
rirv938-anthropic-grpo-73855-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-73855-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-anthropic-grpo-73855-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-anthropic-grpo-73855-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-anthropic-grpo-73855-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-73855-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-anthropic-grpo-73855-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-anthropic-grpo-73855-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-73855-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-anthropic-grpo-73855-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-anthropic-grpo-73855-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-anthropic-grpo-73855-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-73855-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-anthropic-grpo-73855-v1-mkmlizer: Downloaded to shared memory in 89.860s
rirv938-anthropic-grpo-73855-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpq8icnpn4, device:0
rirv938-anthropic-grpo-73855-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-73855-v1-mkmlizer: quantized model in 41.997s
rirv938-anthropic-grpo-73855-v1-mkmlizer: Processed model rirv938/anthropic_grpo_40k_cp1184_99ff_merged in 131.857s
rirv938-anthropic-grpo-73855-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-73855-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-grpo-73855-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-grpo-73855-v1
rirv938-anthropic-grpo-73855-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-73855-v1/config.json
rirv938-anthropic-grpo-73855-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-73855-v1/special_tokens_map.json
rirv938-anthropic-grpo-73855-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-73855-v1/tokenizer_config.json
rirv938-anthropic-grpo-73855-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-73855-v1/tokenizer.json
rirv938-anthropic-grpo-73855-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-grpo-73855-v1/flywheel_model.0.safetensors
rirv938-anthropic-grpo-73855-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.39it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:13, 26.60it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:14, 23.69it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:11, 29.73it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:15, 21.80it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:17, 19.21it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:14, 22.15it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:12, 26.95it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:13, 24.41it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:10, 29.09it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:12, 25.46it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:10, 29.70it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:10, 30.11it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:14, 20.36it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:11, 25.02it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:11, 25.18it/s]
Loading 0:  21%|██        | 77/363 [00:03<00:12, 23.52it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:09, 28.35it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 25.45it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:09, 30.05it/s]
Loading 0:  26%|██▌       | 95/363 [00:03<00:10, 26.16it/s]
Loading 0:  28%|██▊       | 100/363 [00:03<00:08, 30.49it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:12, 20.50it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:10, 25.05it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:10, 23.25it/s]
Loading 0:  33%|███▎      | 118/363 [00:04<00:08, 27.79it/s]
Loading 0:  34%|███▎      | 122/363 [00:04<00:09, 24.95it/s]
Loading 0:  35%|███▍      | 127/363 [00:04<00:08, 29.36it/s]
Loading 0:  36%|███▌      | 131/363 [00:05<00:08, 26.04it/s]
Loading 0:  37%|███▋      | 136/363 [00:05<00:07, 29.76it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:07, 30.27it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:10, 21.67it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:10, 21.05it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:08, 25.62it/s]
Loading 0:  44%|████▎     | 158/363 [00:06<00:08, 23.84it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:06, 28.64it/s]
Loading 0:  46%|████▌     | 167/363 [00:06<00:07, 25.54it/s]
Loading 0:  47%|████▋     | 172/363 [00:06<00:06, 29.38it/s]
Loading 0:  48%|████▊     | 176/363 [00:06<00:07, 26.59it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:07, 25.69it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:08, 22.25it/s]
Loading 0:  53%|█████▎    | 192/363 [00:07<00:05, 28.55it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 26.00it/s]
Loading 0:  55%|█████▌    | 201/363 [00:07<00:05, 28.10it/s]
Loading 0:  56%|█████▌    | 204/363 [00:07<00:06, 26.35it/s]
Loading 0:  58%|█████▊    | 210/363 [00:08<00:04, 30.68it/s]
Loading 0:  59%|█████▉    | 214/363 [00:08<00:05, 29.60it/s]
Loading 0:  60%|██████    | 218/363 [00:08<00:04, 30.02it/s]
Loading 0:  61%|██████▏   | 223/363 [00:08<00:05, 25.44it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:05, 24.32it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:05, 23.48it/s]
Loading 0:  65%|██████▌   | 237/363 [00:09<00:04, 30.32it/s]
Loading 0:  66%|██████▋   | 241/363 [00:09<00:04, 29.15it/s]
Loading 0:  68%|██████▊   | 246/363 [00:09<00:03, 30.98it/s]
Loading 0:  69%|██████▉   | 250/363 [00:09<00:03, 29.63it/s]
Loading 0:  70%|███████   | 255/363 [00:09<00:03, 32.05it/s]
Loading 0:  71%|███████▏  | 259/363 [00:09<00:03, 30.64it/s]
Loading 0:  72%|███████▏  | 263/363 [00:10<00:03, 25.27it/s]
Loading 0:  73%|███████▎  | 266/363 [00:10<00:04, 22.34it/s]
Loading 0:  75%|███████▌  | 273/363 [00:10<00:03, 29.05it/s]
Loading 0:  76%|███████▋  | 277/363 [00:10<00:03, 27.79it/s]
Loading 0:  78%|███████▊  | 282/363 [00:10<00:02, 29.27it/s]
Loading 0:  79%|███████▉  | 286/363 [00:10<00:02, 28.23it/s]
Loading 0:  80%|████████  | 291/363 [00:10<00:02, 30.40it/s]
Loading 0:  81%|████████▏ | 295/363 [00:11<00:02, 29.15it/s]
Loading 0:  82%|████████▏ | 299/363 [00:11<00:02, 29.31it/s]
Loading 0:  84%|████████▎ | 304/363 [00:11<00:02, 25.37it/s]
Loading 0:  85%|████████▍ | 307/363 [00:11<00:02, 23.88it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 22.82it/s]
Loading 0:  87%|████████▋ | 316/363 [00:11<00:01, 28.04it/s]
Loading 0:  88%|████████▊ | 320/363 [00:12<00:01, 24.30it/s]
Loading 0:  90%|████████▉ | 325/363 [00:12<00:01, 27.86it/s]
Loading 0:  91%|█████████ | 329/363 [00:12<00:01, 25.30it/s]
Loading 0:  92%|█████████▏| 334/363 [00:12<00:00, 30.12it/s]
Loading 0:  93%|█████████▎| 338/363 [00:12<00:00, 26.92it/s]
Loading 0:  95%|█████████▍| 344/363 [00:19<00:08,  2.20it/s]
Loading 0:  96%|█████████▌| 348/363 [00:19<00:05,  2.87it/s]
Loading 0:  97%|█████████▋| 353/363 [00:20<00:02,  4.05it/s]
Loading 0:  98%|█████████▊| 357/363 [00:20<00:01,  5.18it/s]
                                                            

Job rirv938-anthropic-grpo-73855-v1-mkmlizer completed after 155.46s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-73855-v1-mkmlizer
Pipeline stage MKMLizer completed in 155.97s
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-73855-v1
Waiting for inference service rirv938-anthropic-grpo-73855-v1 to be ready
Inference service rirv938-anthropic-grpo-73855-v1 ready after 140.44215893745422s
Pipeline stage MKMLDeployer completed in 141.01s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.744690179824829s
Received healthy response to inference request in 1.8820641040802002s
Received healthy response to inference request in 1.6392788887023926s
Received healthy response to inference request in 1.8152809143066406s
Received healthy response to inference request in 1.8396797180175781s
5 requests
0 failed requests
5th percentile: 1.6744792938232422
10th percentile: 1.7096796989440919
20th percentile: 1.780080509185791
30th percentile: 1.8201606750488282
40th percentile: 1.829920196533203
50th percentile: 1.8396797180175781
60th percentile: 1.856633472442627
70th percentile: 1.8735872268676759
80th percentile: 2.0545893192291262
90th percentile: 2.3996397495269775
95th percentile: 2.572164964675903
99th percentile: 2.710185136795044
mean time: 1.984198760986328
Pipeline stage StressChecker completed in 11.41s
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 0.73s
Shutdown handler de-registered
rirv938-anthropic-grpo-_73855_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 2841.00s
Shutdown handler de-registered
rirv938-anthropic-grpo-_73855_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-grpo-_73855_v1 status is now torndown due to DeploymentManager action