rirv938-anthropic-grpo-_74020

developer_uid: rirv938

submission_id: rirv938-anthropic-grpo-_74020_v1

model_name: rirv938-anthropic-grpo-_74020_v1

model_group: rirv938/anthropic_grpo_4

status: torndown

timestamp: 2025-05-15T19:11:49+00:00

num_battles: 8159

num_wins: 4057

celo_rating: 1286.86

family_friendly_score: 0.5516

family_friendly_standard_error: 0.007033312732987209

submission_type: basic

model_repo: rirv938/anthropic_grpo_40k_cp78_95ff_beta6_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': 0.6457632020635827, 'latency_mean': 1.5484751272201538, 'latency_p50': 1.5581631660461426, 'latency_p90': 1.7114426851272584}, {'batch_size': 3, 'throughput': 1.2463833266109832, 'latency_mean': 2.404110119342804, 'latency_p50': 2.402458667755127, 'latency_p90': 2.645118975639343}, {'batch_size': 5, 'throughput': 1.5278096561889354, 'latency_mean': 3.264093837738037, 'latency_p50': 3.252090096473694, 'latency_p90': 3.660328578948975}, {'batch_size': 6, 'throughput': 1.6182654027888184, 'latency_mean': 3.689486927986145, 'latency_p50': 3.694056510925293, 'latency_p90': 4.196827101707458}, {'batch_size': 8, 'throughput': 1.7114142779232169, 'latency_mean': 4.6408188998699185, 'latency_p50': 4.627683877944946, 'latency_p90': 5.241808557510376}, {'batch_size': 10, 'throughput': 1.7636781995817563, 'latency_mean': 5.622770738601685, 'latency_p50': 5.625438094139099, 'latency_p90': 6.438059115409851}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rirv938-anthropic-grpo-_74020_v1

is_internal_developer: True

language_model: rirv938/anthropic_grpo_40k_cp78_95ff_beta6_merged

model_size: 13B

ranking_group: single

throughput_3p7s: 1.63

us_pacific_date: 2025-05-15

win_ratio: 0.49724230910650813

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:', '\n', '</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-74020-v1-mkmlizer
Waiting for job on rirv938-anthropic-grpo-74020-v1-mkmlizer to finish
rirv938-anthropic-grpo-74020-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-grpo-74020-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-anthropic-grpo-74020-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-anthropic-grpo-74020-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-anthropic-grpo-74020-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-anthropic-grpo-74020-v1-mkmlizer: ║       /___/                                                         ║
rirv938-anthropic-grpo-74020-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-74020-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-anthropic-grpo-74020-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-anthropic-grpo-74020-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-anthropic-grpo-74020-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-74020-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-anthropic-grpo-74020-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-anthropic-grpo-74020-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-74020-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-anthropic-grpo-74020-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-anthropic-grpo-74020-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-anthropic-grpo-74020-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-74020-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-anthropic-grpo-74020-v1-mkmlizer: Downloaded to shared memory in 86.297s
rirv938-anthropic-grpo-74020-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpevp437vb, device:0
rirv938-anthropic-grpo-74020-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-74020-v1-mkmlizer: quantized model in 42.949s
rirv938-anthropic-grpo-74020-v1-mkmlizer: Processed model rirv938/anthropic_grpo_40k_cp78_95ff_beta6_merged in 129.247s
rirv938-anthropic-grpo-74020-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-74020-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-grpo-74020-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-grpo-74020-v1
rirv938-anthropic-grpo-74020-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-74020-v1/config.json
rirv938-anthropic-grpo-74020-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-74020-v1/special_tokens_map.json
rirv938-anthropic-grpo-74020-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-74020-v1/tokenizer_config.json
rirv938-anthropic-grpo-74020-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-74020-v1/tokenizer.json
rirv938-anthropic-grpo-74020-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-grpo-74020-v1/flywheel_model.0.safetensors
rirv938-anthropic-grpo-74020-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:17, 20.55it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:14, 25.20it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:15, 22.33it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:12, 28.11it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:16, 20.44it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:18, 18.43it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:13, 23.83it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:13, 23.55it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:13, 24.28it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:14, 22.03it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:12, 26.41it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:13, 23.55it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:11, 27.98it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:10, 29.28it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:15, 18.97it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:12, 23.40it/s]
Loading 0:  20%|██        | 73/363 [00:03<00:12, 23.32it/s]
Loading 0:  21%|██        | 77/363 [00:03<00:13, 21.97it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:10, 26.17it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:11, 23.40it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:09, 27.67it/s]
Loading 0:  26%|██▌       | 95/363 [00:03<00:10, 24.42it/s]
Loading 0:  28%|██▊       | 100/363 [00:04<00:09, 28.59it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:13, 18.91it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:10, 23.24it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:11, 21.80it/s]
Loading 0:  33%|███▎      | 118/363 [00:04<00:09, 26.09it/s]
Loading 0:  34%|███▎      | 122/363 [00:05<00:10, 23.06it/s]
Loading 0:  35%|███▍      | 127/363 [00:05<00:08, 26.89it/s]
Loading 0:  36%|███▌      | 131/363 [00:05<00:09, 23.94it/s]
Loading 0:  37%|███▋      | 136/363 [00:05<00:08, 27.99it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:07, 29.06it/s]
Loading 0:  40%|███▉      | 145/363 [00:06<00:10, 20.48it/s]
Loading 0:  41%|████      | 149/363 [00:06<00:10, 20.04it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:08, 24.38it/s]
Loading 0:  44%|████▎     | 158/363 [00:06<00:09, 22.64it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:07, 26.83it/s]
Loading 0:  46%|████▌     | 167/363 [00:07<00:08, 23.79it/s]
Loading 0:  47%|████▋     | 172/363 [00:07<00:06, 27.80it/s]
Loading 0:  48%|████▊     | 176/363 [00:07<00:07, 24.63it/s]
Loading 0:  50%|████▉     | 181/363 [00:07<00:06, 29.00it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:09, 19.27it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 23.64it/s]
Loading 0:  53%|█████▎    | 194/363 [00:08<00:07, 22.28it/s]
Loading 0:  55%|█████▍    | 199/363 [00:08<00:06, 26.79it/s]
Loading 0:  56%|█████▌    | 203/363 [00:08<00:06, 23.73it/s]
Loading 0:  57%|█████▋    | 208/363 [00:08<00:05, 28.25it/s]
Loading 0:  58%|█████▊    | 212/363 [00:08<00:06, 23.52it/s]
Loading 0:  60%|█████▉    | 217/363 [00:08<00:05, 28.14it/s]
Loading 0:  61%|██████    | 222/363 [00:09<00:04, 29.69it/s]
Loading 0:  62%|██████▏   | 226/363 [00:09<00:06, 21.38it/s]
Loading 0:  63%|██████▎   | 230/363 [00:09<00:06, 20.95it/s]
Loading 0:  65%|██████▍   | 235/363 [00:09<00:04, 25.61it/s]
Loading 0:  66%|██████▌   | 239/363 [00:09<00:05, 23.58it/s]
Loading 0:  67%|██████▋   | 244/363 [00:10<00:04, 28.17it/s]
Loading 0:  68%|██████▊   | 248/363 [00:10<00:04, 25.29it/s]
Loading 0:  70%|██████▉   | 253/363 [00:10<00:03, 29.72it/s]
Loading 0:  71%|███████   | 257/363 [00:10<00:04, 26.40it/s]
Loading 0:  72%|███████▏  | 262/363 [00:10<00:03, 31.16it/s]
Loading 0:  73%|███████▎  | 266/363 [00:11<00:04, 20.84it/s]
Loading 0:  75%|███████▍  | 271/363 [00:11<00:03, 25.59it/s]
Loading 0:  76%|███████▌  | 275/363 [00:11<00:03, 23.56it/s]
Loading 0:  77%|███████▋  | 280/363 [00:11<00:02, 28.32it/s]
Loading 0:  78%|███████▊  | 284/363 [00:11<00:03, 25.35it/s]
Loading 0:  80%|███████▉  | 289/363 [00:11<00:02, 30.16it/s]
Loading 0:  81%|████████  | 293/363 [00:11<00:02, 26.48it/s]
Loading 0:  82%|████████▏ | 298/363 [00:12<00:02, 31.13it/s]
Loading 0:  83%|████████▎ | 303/363 [00:12<00:01, 31.61it/s]
Loading 0:  85%|████████▍ | 307/363 [00:12<00:02, 22.15it/s]
Loading 0:  86%|████████▌ | 311/363 [00:12<00:02, 21.59it/s]
Loading 0:  87%|████████▋ | 316/363 [00:12<00:01, 25.99it/s]
Loading 0:  88%|████████▊ | 320/363 [00:13<00:01, 24.17it/s]
Loading 0:  90%|█████████ | 327/363 [00:13<00:01, 30.41it/s]
Loading 0:  91%|█████████ | 331/363 [00:13<00:01, 27.65it/s]
Loading 0:  92%|█████████▏| 335/363 [00:13<00:01, 27.61it/s]
Loading 0:  93%|█████████▎| 338/363 [00:13<00:01, 22.57it/s]
Loading 0:  94%|█████████▍| 343/363 [00:13<00:00, 27.59it/s]
Loading 0:  96%|█████████▌| 347/363 [00:20<00:08,  1.91it/s]
Loading 0:  96%|█████████▋| 350/363 [00:21<00:05,  2.43it/s]
Loading 0:  97%|█████████▋| 353/363 [00:21<00:03,  3.11it/s]
Loading 0:  98%|█████████▊| 357/363 [00:21<00:01,  4.29it/s]
Loading 0: 100%|█████████▉| 362/363 [00:21<00:00,  6.43it/s]
                                                            
Job rirv938-anthropic-grpo-74020-v1-mkmlizer completed after 155.65s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-74020-v1-mkmlizer
Pipeline stage MKMLizer completed in 156.33s
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-74020-v1
Waiting for inference service rirv938-anthropic-grpo-74020-v1 to be ready
Inference service rirv938-anthropic-grpo-74020-v1 ready after 130.52610087394714s
Pipeline stage MKMLDeployer completed in 131.08s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.57161021232605s
Received healthy response to inference request in 1.9703803062438965s
Received healthy response to inference request in 1.6686441898345947s
Received healthy response to inference request in 1.5905358791351318s
Received healthy response to inference request in 1.8027474880218506s
5 requests
0 failed requests
5th percentile: 1.6061575412750244
10th percentile: 1.621779203414917
20th percentile: 1.6530225276947021
30th percentile: 1.695464849472046
40th percentile: 1.7491061687469482
50th percentile: 1.8027474880218506
60th percentile: 1.869800615310669
70th percentile: 1.9368537425994872
80th percentile: 2.0906262874603274
90th percentile: 2.3311182498931884
95th percentile: 2.451364231109619
99th percentile: 2.5475610160827635
mean time: 1.9207836151123048
Pipeline stage StressChecker completed in 11.09s
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 0.93s
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 0.68s
Shutdown handler de-registered
rirv938-anthropic-grpo-_74020_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 0.11s
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 rirv938-anthropic-grpo-74020-v1-profiler
Waiting for inference service rirv938-anthropic-grpo-74020-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 3004.08s
Shutdown handler de-registered
rirv938-anthropic-grpo-_74020_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-grpo-_74020_v1 status is now torndown due to DeploymentManager action