developer_uid: rirv938
submission_id: rirv938-anthropic-grpo-_44019_v1
model_name: rirv938-anthropic-grpo-_44019_v1
model_group: rirv938/anthropic_grpo_4
status: torndown
timestamp: 2025-04-29T18:27:55+00:00
num_battles: 5834
num_wins: 2962
celo_rating: 1314.47
family_friendly_score: 0.5608
family_friendly_standard_error: 0.007018594731140985
submission_type: basic
model_repo: rirv938/anthropic_grpo_40k_cp148_95ff_merged
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.6053264334161879, 'latency_mean': 1.65193536400795, 'latency_p50': 1.648459553718567, 'latency_p90': 1.8370399236679078}, {'batch_size': 3, 'throughput': 1.1172702719348087, 'latency_mean': 2.674872374534607, 'latency_p50': 2.6692832708358765, 'latency_p90': 2.9470509767532347}, {'batch_size': 5, 'throughput': 1.327036000938761, 'latency_mean': 3.7407867991924286, 'latency_p50': 3.781273365020752, 'latency_p90': 4.162767791748047}, {'batch_size': 6, 'throughput': 1.4042088319920725, 'latency_mean': 4.2434172546863556, 'latency_p50': 4.24582040309906, 'latency_p90': 4.797827529907226}, {'batch_size': 8, 'throughput': 1.4728230597807557, 'latency_mean': 5.392822227478027, 'latency_p50': 5.423691272735596, 'latency_p90': 6.057694149017334}, {'batch_size': 10, 'throughput': 1.5102481553051839, 'latency_mean': 6.584005624055862, 'latency_p50': 6.602865815162659, 'latency_p90': 7.542739081382751}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rirv938-anthropic-grpo-_44019_v1
is_internal_developer: True
language_model: rirv938/anthropic_grpo_40k_cp148_95ff_merged
model_size: 13B
ranking_group: single
throughput_3p7s: 1.33
us_pacific_date: 2025-04-29
win_ratio: 0.5077134041823792
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': 1024, '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-44019-v1-mkmlizer
Waiting for job on rirv938-anthropic-grpo-44019-v1-mkmlizer to finish
rirv938-anthropic-grpo-44019-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-grpo-44019-v1-mkmlizer: ║ _____ __ __ ║
rirv938-anthropic-grpo-44019-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rirv938-anthropic-grpo-44019-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rirv938-anthropic-grpo-44019-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rirv938-anthropic-grpo-44019-v1-mkmlizer: ║ /___/ ║
rirv938-anthropic-grpo-44019-v1-mkmlizer: ║ ║
rirv938-anthropic-grpo-44019-v1-mkmlizer: ║ Version: 0.12.8 ║
rirv938-anthropic-grpo-44019-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rirv938-anthropic-grpo-44019-v1-mkmlizer: ║ https://mk1.ai ║
rirv938-anthropic-grpo-44019-v1-mkmlizer: ║ ║
rirv938-anthropic-grpo-44019-v1-mkmlizer: ║ The license key for the current software has been verified as ║
rirv938-anthropic-grpo-44019-v1-mkmlizer: ║ belonging to: ║
rirv938-anthropic-grpo-44019-v1-mkmlizer: ║ ║
rirv938-anthropic-grpo-44019-v1-mkmlizer: ║ Chai Research Corp. ║
rirv938-anthropic-grpo-44019-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rirv938-anthropic-grpo-44019-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
rirv938-anthropic-grpo-44019-v1-mkmlizer: ║ ║
rirv938-anthropic-grpo-44019-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-anthropic-grpo-44019-v1-mkmlizer: Downloaded to shared memory in 66.303s
rirv938-anthropic-grpo-44019-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_6n1susa, device:0
rirv938-anthropic-grpo-44019-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-44019-v1-mkmlizer: quantized model in 40.693s
rirv938-anthropic-grpo-44019-v1-mkmlizer: Processed model rirv938/anthropic_grpo_40k_cp148_95ff_merged in 106.996s
rirv938-anthropic-grpo-44019-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-44019-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-44019-v1/special_tokens_map.json
rirv938-anthropic-grpo-44019-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-44019-v1/config.json
rirv938-anthropic-grpo-44019-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-44019-v1/tokenizer_config.json
rirv938-anthropic-grpo-44019-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-44019-v1/tokenizer.json
rirv938-anthropic-grpo-44019-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-grpo-44019-v1/flywheel_model.0.safetensors
rirv938-anthropic-grpo-44019-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:15, 23.51it/s] Loading 0: 3%|▎ | 10/363 [00:00<00:12, 29.08it/s] Loading 0: 4%|▍ | 14/363 [00:00<00:13, 26.02it/s] Loading 0: 6%|▌ | 20/363 [00:00<00:09, 35.09it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:13, 24.52it/s] Loading 0: 8%|▊ | 28/363 [00:01<00:13, 24.78it/s] Loading 0: 9%|▉ | 32/363 [00:01<00:13, 23.88it/s] Loading 0: 11%|█ | 39/363 [00:01<00:10, 30.54it/s] Loading 0: 12%|█▏ | 43/363 [00:01<00:10, 29.36it/s] Loading 0: 13%|█▎ | 48/363 [00:01<00:10, 31.50it/s] Loading 0: 14%|█▍ | 52/363 [00:01<00:10, 29.88it/s] Loading 0: 15%|█▌ | 56/363 [00:01<00:10, 30.08it/s] Loading 0: 17%|█▋ | 61/363 [00:02<00:11, 26.22it/s] Loading 0: 18%|█▊ | 64/363 [00:02<00:12, 23.01it/s] Loading 0: 20%|█▉ | 71/363 [00:02<00:09, 29.96it/s] Loading 0: 21%|██ | 75/363 [00:02<00:09, 28.81it/s] Loading 0: 22%|██▏ | 79/363 [00:02<00:10, 28.07it/s] Loading 0: 23%|██▎ | 84/363 [00:02<00:09, 30.65it/s] Loading 0: 24%|██▍ | 88/363 [00:03<00:09, 29.30it/s] Loading 0: 26%|██▌ | 93/363 [00:03<00:08, 31.49it/s] Loading 0: 27%|██▋ | 97/363 [00:03<00:08, 30.06it/s] Loading 0: 28%|██▊ | 101/363 [00:03<00:10, 24.27it/s] Loading 0: 29%|██▊ | 104/363 [00:03<00:11, 21.61it/s] Loading 0: 31%|███ | 111/363 [00:03<00:08, 28.62it/s] Loading 0: 32%|███▏ | 115/363 [00:04<00:08, 28.19it/s] Loading 0: 33%|███▎ | 120/363 [00:04<00:07, 30.68it/s] Loading 0: 34%|███▍ | 124/363 [00:04<00:08, 29.69it/s] Loading 0: 36%|███▌ | 129/363 [00:04<00:07, 31.94it/s] Loading 0: 37%|███▋ | 133/363 [00:04<00:07, 30.13it/s] Loading 0: 38%|███▊ | 137/363 [00:04<00:07, 29.54it/s] Loading 0: 39%|███▉ | 141/363 [00:04<00:07, 31.57it/s] Loading 0: 40%|███▉ | 145/363 [00:05<00:09, 22.79it/s] Loading 0: 41%|████ | 149/363 [00:05<00:09, 22.52it/s] Loading 0: 43%|████▎ | 156/363 [00:05<00:07, 29.39it/s] Loading 0: 44%|████▍ | 160/363 [00:05<00:07, 28.99it/s] Loading 0: 45%|████▌ | 165/363 [00:05<00:06, 31.60it/s] Loading 0: 47%|████▋ | 169/363 [00:05<00:06, 30.14it/s] Loading 0: 48%|████▊ | 174/363 [00:06<00:05, 31.82it/s] Loading 0: 49%|████▉ | 178/363 [00:06<00:06, 30.52it/s] Loading 0: 50%|█████ | 182/363 [00:06<00:07, 24.67it/s] Loading 0: 51%|█████ | 185/363 [00:06<00:08, 22.00it/s] Loading 0: 53%|█████▎ | 192/363 [00:06<00:05, 28.89it/s] Loading 0: 54%|█████▍ | 196/363 [00:06<00:05, 28.23it/s] Loading 0: 55%|█████▌ | 201/363 [00:07<00:05, 30.85it/s] Loading 0: 56%|█████▋ | 205/363 [00:07<00:05, 29.74it/s] Loading 0: 58%|█████▊ | 210/363 [00:07<00:04, 31.16it/s] Loading 0: 59%|█████▉ | 214/363 [00:07<00:05, 29.74it/s] Loading 0: 60%|██████ | 218/363 [00:07<00:04, 29.71it/s] Loading 0: 61%|██████▏ | 223/363 [00:07<00:05, 25.68it/s] Loading 0: 62%|██████▏ | 226/363 [00:08<00:05, 24.57it/s] Loading 0: 63%|██████▎ | 230/363 [00:08<00:05, 23.44it/s] Loading 0: 65%|██████▌ | 237/363 [00:08<00:04, 28.36it/s] Loading 0: 66%|██████▌ | 240/363 [00:08<00:04, 26.49it/s] Loading 0: 68%|██████▊ | 246/363 [00:08<00:03, 30.59it/s] Loading 0: 69%|██████▉ | 250/363 [00:08<00:03, 29.53it/s] Loading 0: 70%|███████ | 255/363 [00:09<00:03, 30.59it/s] Loading 0: 71%|███████▏ | 259/363 [00:09<00:03, 28.64it/s] Loading 0: 72%|███████▏ | 263/363 [00:09<00:04, 23.37it/s] Loading 0: 73%|███████▎ | 266/363 [00:09<00:04, 20.89it/s] Loading 0: 75%|███████▍ | 272/363 [00:09<00:03, 28.11it/s] Loading 0: 76%|███████▌ | 276/363 [00:09<00:03, 25.45it/s] Loading 0: 77%|███████▋ | 280/363 [00:10<00:02, 28.32it/s] Loading 0: 78%|███████▊ | 284/363 [00:10<00:03, 25.48it/s] Loading 0: 80%|███████▉ | 290/363 [00:10<00:02, 32.62it/s] Loading 0: 81%|████████ | 294/363 [00:10<00:02, 27.97it/s] Loading 0: 82%|████████▏ | 299/363 [00:10<00:02, 29.68it/s] Loading 0: 83%|████████▎ | 303/363 [00:10<00:01, 31.59it/s] Loading 0: 85%|████████▍ | 307/363 [00:11<00:02, 22.24it/s] Loading 0: 86%|████████▌ | 311/363 [00:11<00:02, 21.96it/s] Loading 0: 88%|████████▊ | 318/363 [00:11<00:01, 28.46it/s] Loading 0: 89%|████████▊ | 322/363 [00:11<00:01, 27.96it/s] Loading 0: 90%|█████████ | 327/363 [00:11<00:01, 30.04it/s] Loading 0: 91%|█████████ | 331/363 [00:11<00:01, 29.09it/s] Loading 0: 93%|█████████▎| 336/363 [00:12<00:00, 31.61it/s] Loading 0: 94%|█████████▎| 340/363 [00:12<00:00, 29.63it/s] Loading 0: 95%|█████████▍| 344/363 [00:19<00:09, 2.01it/s] Loading 0: 96%|█████████▌| 348/363 [00:19<00:05, 2.70it/s] Loading 0: 97%|█████████▋| 353/363 [00:19<00:02, 3.90it/s] Loading 0: 98%|█████████▊| 357/363 [00:19<00:01, 5.02it/s] Loading 0: 100%|█████████▉| 362/363 [00:19<00:00, 7.15it/s]
Job rirv938-anthropic-grpo-44019-v1-mkmlizer completed after 136.09s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-44019-v1-mkmlizer
Pipeline stage MKMLizer completed in 136.63s
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-44019-v1
Waiting for inference service rirv938-anthropic-grpo-44019-v1 to be ready
Inference service rirv938-anthropic-grpo-44019-v1 ready after 140.47386598587036s
Pipeline stage MKMLDeployer completed in 140.93s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3488805294036865s
Received healthy response to inference request in 1.7317070960998535s
Received healthy response to inference request in 1.9976472854614258s
Received healthy response to inference request in 2.099297046661377s
Received healthy response to inference request in 1.727046012878418s
5 requests
0 failed requests
5th percentile: 1.727978229522705
10th percentile: 1.7289104461669922
20th percentile: 1.7307748794555664
30th percentile: 1.784895133972168
40th percentile: 1.891271209716797
50th percentile: 1.9976472854614258
60th percentile: 2.0383071899414062
70th percentile: 2.0789670944213867
80th percentile: 2.149213743209839
90th percentile: 2.249047136306763
95th percentile: 2.2989638328552244
99th percentile: 2.338897190093994
mean time: 1.9809155941009522
Pipeline stage StressChecker completed in 11.21s
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 0.94s
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 0.78s
Shutdown handler de-registered
rirv938-anthropic-grpo-_44019_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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-anthropic-grpo-44019-v1-profiler
Waiting for inference service rirv938-anthropic-grpo-44019-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 3073.08s
Shutdown handler de-registered
rirv938-anthropic-grpo-_44019_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-grpo-_44019_v1 status is now torndown due to DeploymentManager action