developer_uid: rirv938
submission_id: rirv938-anthropic-grpo-_51376_v4
model_name: rirv938-anthropic-grpo-_51376_v4
model_group: rirv938/anthropic_grpo_4
status: torndown
timestamp: 2025-05-13T17:20:24+00:00
num_battles: 6523
num_wins: 3405
celo_rating: 1304.6
family_friendly_score: 0.5508
family_friendly_standard_error: 0.007034477379308288
submission_type: basic
model_repo: rirv938/anthropic_grpo_40k_cp592_95ff_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': 0.6447809118357272, 'latency_mean': 1.5508509516716003, 'latency_p50': 1.5545114278793335, 'latency_p90': 1.7227361917495727}, {'batch_size': 3, 'throughput': 1.2351017811768523, 'latency_mean': 2.4195199489593504, 'latency_p50': 2.4099520444869995, 'latency_p90': 2.705056381225586}, {'batch_size': 5, 'throughput': 1.5325699925533423, 'latency_mean': 3.237409633398056, 'latency_p50': 3.2641953229904175, 'latency_p90': 3.5814661026000976}, {'batch_size': 6, 'throughput': 1.6193246403831953, 'latency_mean': 3.6769781053066253, 'latency_p50': 3.688033938407898, 'latency_p90': 4.058049321174622}, {'batch_size': 8, 'throughput': 1.7277908929049879, 'latency_mean': 4.593096590042114, 'latency_p50': 4.633475422859192, 'latency_p90': 5.112503123283386}, {'batch_size': 10, 'throughput': 1.7622882736165248, 'latency_mean': 5.633519710302353, 'latency_p50': 5.6397223472595215, 'latency_p90': 6.380242133140564}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rirv938-anthropic-grpo-_51376_v4
is_internal_developer: True
language_model: rirv938/anthropic_grpo_40k_cp592_95ff_merged
model_size: 13B
ranking_group: single
throughput_3p7s: 1.64
us_pacific_date: 2025-05-13
win_ratio: 0.5219990801778323
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-51376-v4-mkmlizer
Waiting for job on rirv938-anthropic-grpo-51376-v4-mkmlizer to finish
rirv938-anthropic-grpo-51376-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-grpo-51376-v4-mkmlizer: ║ _____ __ __ ║
rirv938-anthropic-grpo-51376-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rirv938-anthropic-grpo-51376-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rirv938-anthropic-grpo-51376-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rirv938-anthropic-grpo-51376-v4-mkmlizer: ║ /___/ ║
rirv938-anthropic-grpo-51376-v4-mkmlizer: ║ ║
rirv938-anthropic-grpo-51376-v4-mkmlizer: ║ Version: 0.12.8 ║
rirv938-anthropic-grpo-51376-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rirv938-anthropic-grpo-51376-v4-mkmlizer: ║ https://mk1.ai ║
rirv938-anthropic-grpo-51376-v4-mkmlizer: ║ ║
rirv938-anthropic-grpo-51376-v4-mkmlizer: ║ The license key for the current software has been verified as ║
rirv938-anthropic-grpo-51376-v4-mkmlizer: ║ belonging to: ║
rirv938-anthropic-grpo-51376-v4-mkmlizer: ║ ║
rirv938-anthropic-grpo-51376-v4-mkmlizer: ║ Chai Research Corp. ║
rirv938-anthropic-grpo-51376-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rirv938-anthropic-grpo-51376-v4-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
rirv938-anthropic-grpo-51376-v4-mkmlizer: ║ ║
rirv938-anthropic-grpo-51376-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-anthropic-grpo-51376-v4-mkmlizer: Downloaded to shared memory in 110.426s
rirv938-anthropic-grpo-51376-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpni87y2_v, device:0
rirv938-anthropic-grpo-51376-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-51376-v4-mkmlizer: quantized model in 43.271s
rirv938-anthropic-grpo-51376-v4-mkmlizer: Processed model rirv938/anthropic_grpo_40k_cp592_95ff_merged in 153.697s
rirv938-anthropic-grpo-51376-v4-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-51376-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-grpo-51376-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-grpo-51376-v4
rirv938-anthropic-grpo-51376-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-51376-v4/config.json
rirv938-anthropic-grpo-51376-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-51376-v4/special_tokens_map.json
rirv938-anthropic-grpo-51376-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-51376-v4/tokenizer_config.json
rirv938-anthropic-grpo-51376-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-51376-v4/tokenizer.json
rirv938-anthropic-grpo-51376-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-grpo-51376-v4/flywheel_model.0.safetensors
rirv938-anthropic-grpo-51376-v4-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:15, 22.62it/s] Loading 0: 3%|▎ | 10/363 [00:00<00:12, 28.19it/s] Loading 0: 4%|▍ | 14/363 [00:00<00:13, 25.03it/s] Loading 0: 6%|▌ | 20/363 [00:00<00:10, 33.88it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:15, 22.53it/s] Loading 0: 7%|▋ | 27/363 [00:01<00:15, 21.49it/s] Loading 0: 9%|▊ | 31/363 [00:01<00:13, 25.21it/s] Loading 0: 10%|▉ | 35/363 [00:01<00:12, 26.23it/s] Loading 0: 11%|█ | 39/363 [00:01<00:11, 27.44it/s] Loading 0: 12%|█▏ | 43/363 [00:01<00:12, 25.37it/s] Loading 0: 13%|█▎ | 46/363 [00:01<00:12, 24.89it/s] Loading 0: 14%|█▍ | 50/363 [00:02<00:13, 22.69it/s] Loading 0: 15%|█▌ | 55/363 [00:02<00:11, 27.66it/s] Loading 0: 17%|█▋ | 60/363 [00:02<00:10, 28.30it/s] Loading 0: 18%|█▊ | 64/363 [00:02<00:15, 18.97it/s] Loading 0: 19%|█▉ | 69/363 [00:02<00:12, 23.36it/s] Loading 0: 20%|█▉ | 72/363 [00:02<00:13, 21.83it/s] Loading 0: 21%|██ | 77/363 [00:03<00:12, 22.34it/s] Loading 0: 23%|██▎ | 82/363 [00:03<00:10, 26.63it/s] Loading 0: 24%|██▎ | 86/363 [00:03<00:11, 23.98it/s] Loading 0: 25%|██▌ | 91/363 [00:03<00:09, 28.40it/s] Loading 0: 26%|██▌ | 95/363 [00:03<00:10, 24.71it/s] Loading 0: 28%|██▊ | 100/363 [00:03<00:09, 29.06it/s] Loading 0: 29%|██▊ | 104/363 [00:04<00:13, 19.16it/s] Loading 0: 30%|███ | 109/363 [00:04<00:10, 23.73it/s] Loading 0: 31%|███ | 113/363 [00:04<00:11, 22.01it/s] Loading 0: 33%|███▎ | 118/363 [00:04<00:09, 26.57it/s] Loading 0: 34%|███▎ | 122/363 [00:04<00:10, 23.99it/s] Loading 0: 35%|███▍ | 127/363 [00:05<00:08, 28.15it/s] Loading 0: 36%|███▌ | 131/363 [00:05<00:09, 24.48it/s] Loading 0: 37%|███▋ | 136/363 [00:05<00:07, 28.73it/s] Loading 0: 39%|███▉ | 141/363 [00:05<00:07, 29.62it/s] Loading 0: 40%|███▉ | 145/363 [00:05<00:10, 20.93it/s] Loading 0: 41%|████ | 149/363 [00:06<00:10, 20.31it/s] Loading 0: 42%|████▏ | 154/363 [00:06<00:08, 24.78it/s] Loading 0: 44%|████▎ | 158/363 [00:06<00:09, 22.63it/s] Loading 0: 45%|████▍ | 163/363 [00:06<00:07, 27.06it/s] Loading 0: 46%|████▌ | 167/363 [00:06<00:07, 24.53it/s] Loading 0: 47%|████▋ | 172/363 [00:06<00:06, 29.19it/s] Loading 0: 48%|████▊ | 176/363 [00:07<00:07, 25.13it/s] Loading 0: 50%|████▉ | 181/363 [00:07<00:06, 29.46it/s] Loading 0: 51%|█████ | 185/363 [00:07<00:09, 19.63it/s] Loading 0: 52%|█████▏ | 190/363 [00:07<00:07, 24.14it/s] Loading 0: 53%|█████▎ | 194/363 [00:07<00:07, 22.46it/s] Loading 0: 55%|█████▍ | 199/363 [00:08<00:06, 26.94it/s] Loading 0: 56%|█████▌ | 203/363 [00:08<00:06, 24.29it/s] Loading 0: 57%|█████▋ | 208/363 [00:08<00:05, 28.45it/s] Loading 0: 58%|█████▊ | 212/363 [00:08<00:05, 25.40it/s] Loading 0: 60%|█████▉ | 217/363 [00:08<00:04, 29.69it/s] Loading 0: 61%|██████ | 222/363 [00:08<00:04, 30.37it/s] Loading 0: 62%|██████▏ | 226/363 [00:09<00:06, 21.48it/s] Loading 0: 63%|██████▎ | 230/363 [00:09<00:06, 20.85it/s] Loading 0: 65%|██████▍ | 235/363 [00:09<00:05, 25.40it/s] Loading 0: 66%|██████▌ | 239/363 [00:09<00:05, 23.25it/s] Loading 0: 67%|██████▋ | 244/363 [00:09<00:04, 27.69it/s] Loading 0: 68%|██████▊ | 248/363 [00:10<00:04, 24.98it/s] Loading 0: 70%|██████▉ | 253/363 [00:10<00:03, 29.45it/s] Loading 0: 71%|███████ | 257/363 [00:10<00:04, 25.71it/s] Loading 0: 72%|███████▏ | 262/363 [00:10<00:03, 30.02it/s] Loading 0: 73%|███████▎ | 266/363 [00:10<00:04, 20.06it/s] Loading 0: 75%|███████▍ | 271/363 [00:10<00:03, 24.42it/s] Loading 0: 76%|███████▌ | 275/363 [00:11<00:03, 22.63it/s] Loading 0: 77%|███████▋ | 280/363 [00:11<00:03, 27.05it/s] Loading 0: 78%|███████▊ | 284/363 [00:11<00:03, 24.32it/s] Loading 0: 80%|███████▉ | 289/363 [00:11<00:02, 28.71it/s] Loading 0: 81%|████████ | 293/363 [00:11<00:02, 25.33it/s] Loading 0: 82%|████████▏ | 298/363 [00:11<00:02, 29.60it/s] Loading 0: 83%|████████▎ | 303/363 [00:12<00:01, 30.02it/s] Loading 0: 85%|████████▍ | 307/363 [00:12<00:02, 21.32it/s] Loading 0: 86%|████████▌ | 311/363 [00:12<00:02, 20.84it/s] Loading 0: 87%|████████▋ | 316/363 [00:12<00:01, 25.28it/s] Loading 0: 88%|████████▊ | 320/363 [00:12<00:01, 23.28it/s] Loading 0: 90%|████████▉ | 325/363 [00:13<00:01, 27.88it/s] Loading 0: 91%|█████████ | 329/363 [00:13<00:01, 25.08it/s] Loading 0: 92%|█████████▏| 334/363 [00:13<00:01, 27.55it/s] Loading 0: 93%|█████████▎| 338/363 [00:13<00:01, 24.45it/s] Loading 0: 94%|█████████▍| 343/363 [00:13<00:00, 28.88it/s] Loading 0: 96%|█████████▌| 347/363 [00:20<00:08, 1.98it/s] Loading 0: 96%|█████████▋| 350/363 [00:20<00:05, 2.50it/s] Loading 0: 97%|█████████▋| 353/363 [00:20<00:03, 3.19it/s] Loading 0: 98%|█████████▊| 357/363 [00:21<00:01, 4.37it/s]
Job rirv938-anthropic-grpo-51376-v4-mkmlizer completed after 178.22s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-51376-v4-mkmlizer
Pipeline stage MKMLizer completed in 178.82s
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-51376-v4
Waiting for inference service rirv938-anthropic-grpo-51376-v4 to be ready
Inference service rirv938-anthropic-grpo-51376-v4 ready after 120.75962781906128s
Pipeline stage MKMLDeployer completed in 121.31s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.446502923965454s
Received healthy response to inference request in 1.8186347484588623s
Received healthy response to inference request in 2.0163445472717285s
Received healthy response to inference request in 1.6426582336425781s
Received healthy response to inference request in 1.5579135417938232s
5 requests
0 failed requests
5th percentile: 1.5748624801635742
10th percentile: 1.5918114185333252
20th percentile: 1.6257092952728271
30th percentile: 1.677853536605835
40th percentile: 1.7482441425323487
50th percentile: 1.8186347484588623
60th percentile: 1.8977186679840088
70th percentile: 1.9768025875091553
80th percentile: 2.1023762226104736
90th percentile: 2.274439573287964
95th percentile: 2.360471248626709
99th percentile: 2.429296588897705
mean time: 1.8964107990264893
Pipeline stage StressChecker completed in 10.83s
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 0.76s
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 0.63s
Shutdown handler de-registered
rirv938-anthropic-grpo-_51376_v4 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 2734.80s
Shutdown handler de-registered
rirv938-anthropic-grpo-_51376_v4 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-grpo-_51376_v4 status is now torndown due to DeploymentManager action