developer_uid: rirv938
submission_id: rirv938-anthropic-grpo-_98044_v1
model_name: rirv938-anthropic-grpo-_98044_v1
model_group: rirv938/anthropic_grpo_4
status: torndown
timestamp: 2025-05-13T18:24:11+00:00
num_battles: 6952
num_wins: 3632
celo_rating: 1298.92
family_friendly_score: 0.5484
family_friendly_standard_error: 0.007037861038696345
submission_type: basic
model_repo: rirv938/anthropic_grpo_40k_cp148_95ff_6ww_v2_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': 0.6449120648100658, 'latency_mean': 1.5504985511302949, 'latency_p50': 1.5549602508544922, 'latency_p90': 1.7163086891174317}, {'batch_size': 3, 'throughput': 1.2338308773247089, 'latency_mean': 2.426358675956726, 'latency_p50': 2.3976062536239624, 'latency_p90': 2.7260607957839964}, {'batch_size': 5, 'throughput': 1.5162323118735097, 'latency_mean': 3.2763716757297514, 'latency_p50': 3.2955108880996704, 'latency_p90': 3.636079454421997}, {'batch_size': 6, 'throughput': 1.6065352364697592, 'latency_mean': 3.7130887484550477, 'latency_p50': 3.733253598213196, 'latency_p90': 4.1706703186035154}, {'batch_size': 8, 'throughput': 1.6844268451062663, 'latency_mean': 4.7161889743804934, 'latency_p50': 4.676560044288635, 'latency_p90': 5.274486780166626}, {'batch_size': 10, 'throughput': 1.7414147355573548, 'latency_mean': 5.696767246723175, 'latency_p50': 5.745441675186157, 'latency_p90': 6.45416829586029}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rirv938-anthropic-grpo-_98044_v1
is_internal_developer: True
language_model: rirv938/anthropic_grpo_40k_cp148_95ff_6ww_v2_merged
model_size: 13B
ranking_group: single
throughput_3p7s: 1.61
us_pacific_date: 2025-05-13
win_ratio: 0.522439585730725
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': ['\n', 'You:', '</s>', '###'], '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-98044-v1-mkmlizer
Waiting for job on rirv938-anthropic-grpo-98044-v1-mkmlizer to finish
rirv938-anthropic-grpo-98044-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-grpo-98044-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-anthropic-grpo-98044-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-anthropic-grpo-98044-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-anthropic-grpo-98044-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-anthropic-grpo-98044-v1-mkmlizer: ║       /___/                                                         ║
rirv938-anthropic-grpo-98044-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-98044-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-anthropic-grpo-98044-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-anthropic-grpo-98044-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-anthropic-grpo-98044-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-98044-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-anthropic-grpo-98044-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-anthropic-grpo-98044-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-98044-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-anthropic-grpo-98044-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-anthropic-grpo-98044-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-anthropic-grpo-98044-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-98044-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-anthropic-grpo-98044-v1-mkmlizer: Downloaded to shared memory in 77.921s
rirv938-anthropic-grpo-98044-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpalsve4iu, device:0
rirv938-anthropic-grpo-98044-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-98044-v1-mkmlizer: quantized model in 41.251s
rirv938-anthropic-grpo-98044-v1-mkmlizer: Processed model rirv938/anthropic_grpo_40k_cp148_95ff_6ww_v2_merged in 119.173s
rirv938-anthropic-grpo-98044-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-98044-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-grpo-98044-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-grpo-98044-v1
rirv938-anthropic-grpo-98044-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-98044-v1/config.json
rirv938-anthropic-grpo-98044-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-98044-v1/special_tokens_map.json
rirv938-anthropic-grpo-98044-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-98044-v1/tokenizer_config.json
rirv938-anthropic-grpo-98044-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-98044-v1/tokenizer.json
rirv938-anthropic-grpo-98044-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-grpo-98044-v1/flywheel_model.0.safetensors
rirv938-anthropic-grpo-98044-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:17, 20.62it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:13, 25.66it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:15, 23.06it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:11, 29.18it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:16, 20.71it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:17, 18.86it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:13, 24.63it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:12, 25.94it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:12, 26.88it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:12, 25.99it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:12, 26.22it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:13, 23.21it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:11, 27.89it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:10, 28.78it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:15, 18.88it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:12, 23.31it/s]
Loading 0:  20%|██        | 73/363 [00:03<00:12, 23.93it/s]
Loading 0:  21%|██        | 77/363 [00:03<00:12, 23.21it/s]
Loading 0:  23%|██▎       | 84/363 [00:03<00:09, 29.48it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:09, 28.27it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:08, 30.07it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:09, 28.89it/s]
Loading 0:  28%|██▊       | 101/363 [00:04<00:11, 23.22it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:12, 20.89it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:09, 27.44it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:09, 25.44it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 29.61it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 27.96it/s]
Loading 0:  35%|███▌      | 128/363 [00:04<00:07, 30.45it/s]
Loading 0:  36%|███▋      | 132/363 [00:05<00:08, 26.72it/s]
Loading 0:  38%|███▊      | 137/363 [00:05<00:07, 29.09it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 25.13it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:09, 24.12it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:10, 21.04it/s]
Loading 0:  43%|████▎     | 156/363 [00:06<00:07, 27.52it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:07, 27.43it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:06, 30.14it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:06, 29.59it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:05, 32.10it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:05, 30.95it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:07, 25.53it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:07, 22.58it/s]
Loading 0:  53%|█████▎    | 192/363 [00:07<00:05, 29.41it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:05, 28.64it/s]
Loading 0:  55%|█████▌    | 201/363 [00:07<00:05, 30.86it/s]
Loading 0:  56%|█████▋    | 205/363 [00:07<00:05, 29.75it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:04, 31.97it/s]
Loading 0:  59%|█████▉    | 214/363 [00:08<00:05, 29.77it/s]
Loading 0:  60%|██████    | 218/363 [00:08<00:04, 29.78it/s]
Loading 0:  61%|██████▏   | 223/363 [00:08<00:05, 25.64it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:05, 23.57it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:05, 22.97it/s]
Loading 0:  65%|██████▌   | 236/363 [00:08<00:04, 30.20it/s]
Loading 0:  66%|██████▌   | 240/363 [00:09<00:04, 26.87it/s]
Loading 0:  68%|██████▊   | 246/363 [00:09<00:03, 30.71it/s]
Loading 0:  69%|██████▉   | 250/363 [00:09<00:03, 29.60it/s]
Loading 0:  70%|███████   | 255/363 [00:09<00:03, 31.80it/s]
Loading 0:  71%|███████▏  | 259/363 [00:09<00:03, 30.18it/s]
Loading 0:  72%|███████▏  | 263/363 [00:09<00:04, 24.57it/s]
Loading 0:  73%|███████▎  | 266/363 [00:10<00:04, 22.08it/s]
Loading 0:  75%|███████▌  | 273/363 [00:10<00:03, 28.66it/s]
Loading 0:  76%|███████▋  | 277/363 [00:10<00:03, 27.40it/s]
Loading 0:  77%|███████▋  | 280/363 [00:10<00:03, 27.61it/s]
Loading 0:  78%|███████▊  | 284/363 [00:10<00:03, 24.01it/s]
Loading 0:  80%|███████▉  | 289/363 [00:10<00:02, 29.11it/s]
Loading 0:  81%|████████  | 293/363 [00:11<00:02, 25.67it/s]
Loading 0:  82%|████████▏ | 298/363 [00:11<00:02, 30.57it/s]
Loading 0:  83%|████████▎ | 303/363 [00:11<00:01, 31.72it/s]
Loading 0:  85%|████████▍ | 307/363 [00:11<00:02, 22.22it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 21.43it/s]
Loading 0:  87%|████████▋ | 316/363 [00:11<00:01, 26.40it/s]
Loading 0:  88%|████████▊ | 320/363 [00:12<00:01, 24.58it/s]
Loading 0:  90%|████████▉ | 325/363 [00:12<00:01, 28.92it/s]
Loading 0:  91%|█████████ | 329/363 [00:12<00:01, 25.96it/s]
Loading 0:  92%|█████████▏| 334/363 [00:12<00:00, 30.55it/s]
Loading 0:  93%|█████████▎| 338/363 [00:12<00:00, 26.83it/s]
Loading 0:  94%|█████████▍| 343/363 [00:12<00:00, 31.44it/s]
Loading 0:  96%|█████████▌| 347/363 [00:19<00:07,  2.03it/s]
Loading 0:  96%|█████████▋| 350/363 [00:19<00:05,  2.56it/s]
Loading 0:  97%|█████████▋| 353/363 [00:20<00:03,  3.25it/s]
Loading 0:  98%|█████████▊| 357/363 [00:20<00:01,  4.44it/s]
Loading 0: 100%|█████████▉| 362/363 [00:20<00:00,  6.60it/s]
                                                            

Job rirv938-anthropic-grpo-98044-v1-mkmlizer completed after 146.87s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-98044-v1-mkmlizer
Pipeline stage MKMLizer completed in 147.55s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-anthropic-grpo-98044-v1
Waiting for inference service rirv938-anthropic-grpo-98044-v1 to be ready
Inference service rirv938-anthropic-grpo-98044-v1 ready after 120.48866987228394s
Pipeline stage MKMLDeployer completed in 121.02s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.50718092918396s
Received healthy response to inference request in 1.6353662014007568s
Received healthy response to inference request in 1.7781181335449219s
Received healthy response to inference request in 1.821199893951416s
Received healthy response to inference request in 1.7874398231506348s
5 requests
0 failed requests
5th percentile: 1.6639165878295898
10th percentile: 1.6924669742584229
20th percentile: 1.7495677471160889
30th percentile: 1.7799824714660644
40th percentile: 1.7837111473083496
50th percentile: 1.7874398231506348
60th percentile: 1.8009438514709473
70th percentile: 1.8144478797912598
80th percentile: 1.958396100997925
90th percentile: 2.2327885150909426
95th percentile: 2.369984722137451
99th percentile: 2.4797416877746583
mean time: 1.905860996246338
Pipeline stage StressChecker completed in 10.98s
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 0.85s
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 0.69s
Shutdown handler de-registered
rirv938-anthropic-grpo-_98044_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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-anthropic-grpo-98044-v1-profiler
Waiting for inference service rirv938-anthropic-grpo-98044-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 2897.73s
Shutdown handler de-registered
rirv938-anthropic-grpo-_98044_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-grpo-_98044_v1 status is now torndown due to DeploymentManager action