developer_uid: rirv938
submission_id: rirv938-rinen-grpo-40k-_56847_v1
model_name: rirv938-rinen-grpo-40k-_56847_v1
model_group: rirv938/rinen_grpo_40k_c
status: torndown
timestamp: 2025-04-30T15:03:22+00:00
num_battles: 8219
num_wins: 4333
celo_rating: 1323.1
family_friendly_score: 0.55
family_friendly_standard_error: 0.007035623639735145
submission_type: basic
model_repo: rirv938/rinen_grpo_40k_cp296_95ff_run2_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': 0.6024381197423367, 'latency_mean': 1.6598615729808808, 'latency_p50': 1.6655962467193604, 'latency_p90': 1.8305984735488892}, {'batch_size': 3, 'throughput': 1.0856739694463609, 'latency_mean': 2.7504731285572053, 'latency_p50': 2.7373334169387817, 'latency_p90': 3.0865177392959593}, {'batch_size': 5, 'throughput': 1.3096296964443748, 'latency_mean': 3.794340969324112, 'latency_p50': 3.795843720436096, 'latency_p90': 4.316487431526184}, {'batch_size': 6, 'throughput': 1.3687373590855427, 'latency_mean': 4.3685970675945285, 'latency_p50': 4.341321706771851, 'latency_p90': 4.888823103904724}, {'batch_size': 8, 'throughput': 1.4317373757382184, 'latency_mean': 5.545205335617066, 'latency_p50': 5.531261205673218, 'latency_p90': 6.264558744430542}, {'batch_size': 10, 'throughput': 1.473477603210095, 'latency_mean': 6.737676770687103, 'latency_p50': 6.733102083206177, 'latency_p90': 7.641674423217774}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rirv938-rinen-grpo-40k-_56847_v1
is_internal_developer: True
language_model: rirv938/rinen_grpo_40k_cp296_95ff_run2_merged
model_size: 13B
ranking_group: single
throughput_3p7s: 1.3
us_pacific_date: 2025-04-30
win_ratio: 0.527193089183599
generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '####', '</s>', '<|eot_id|>', 'Bot:', 'User:', 'You:', '<|im_end|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': True}
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-rinen-grpo-40k-56847-v1-mkmlizer
Waiting for job on rirv938-rinen-grpo-40k-56847-v1-mkmlizer to finish
rirv938-rinen-grpo-40k-56847-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-rinen-grpo-40k-56847-v1-mkmlizer: ║ _____ __ __ ║
rirv938-rinen-grpo-40k-56847-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rirv938-rinen-grpo-40k-56847-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rirv938-rinen-grpo-40k-56847-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rirv938-rinen-grpo-40k-56847-v1-mkmlizer: ║ /___/ ║
rirv938-rinen-grpo-40k-56847-v1-mkmlizer: ║ ║
rirv938-rinen-grpo-40k-56847-v1-mkmlizer: ║ Version: 0.12.8 ║
rirv938-rinen-grpo-40k-56847-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rirv938-rinen-grpo-40k-56847-v1-mkmlizer: ║ https://mk1.ai ║
rirv938-rinen-grpo-40k-56847-v1-mkmlizer: ║ ║
rirv938-rinen-grpo-40k-56847-v1-mkmlizer: ║ The license key for the current software has been verified as ║
rirv938-rinen-grpo-40k-56847-v1-mkmlizer: ║ belonging to: ║
rirv938-rinen-grpo-40k-56847-v1-mkmlizer: ║ ║
rirv938-rinen-grpo-40k-56847-v1-mkmlizer: ║ Chai Research Corp. ║
rirv938-rinen-grpo-40k-56847-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rirv938-rinen-grpo-40k-56847-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
rirv938-rinen-grpo-40k-56847-v1-mkmlizer: ║ ║
rirv938-rinen-grpo-40k-56847-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-rinen-grpo-40k-56847-v1-mkmlizer: Downloaded to shared memory in 86.981s
rirv938-rinen-grpo-40k-56847-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpujl7px0q, device:0
rirv938-rinen-grpo-40k-56847-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-rinen-grpo-40k-56847-v1-mkmlizer: quantized model in 41.830s
rirv938-rinen-grpo-40k-56847-v1-mkmlizer: Processed model rirv938/rinen_grpo_40k_cp296_95ff_run2_merged in 128.812s
rirv938-rinen-grpo-40k-56847-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-rinen-grpo-40k-56847-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-rinen-grpo-40k-56847-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-rinen-grpo-40k-56847-v1
rirv938-rinen-grpo-40k-56847-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-rinen-grpo-40k-56847-v1/config.json
rirv938-rinen-grpo-40k-56847-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-rinen-grpo-40k-56847-v1/special_tokens_map.json
rirv938-rinen-grpo-40k-56847-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-rinen-grpo-40k-56847-v1/tokenizer_config.json
rirv938-rinen-grpo-40k-56847-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-rinen-grpo-40k-56847-v1/tokenizer.json
rirv938-rinen-grpo-40k-56847-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-rinen-grpo-40k-56847-v1/flywheel_model.0.safetensors
rirv938-rinen-grpo-40k-56847-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:16, 21.77it/s] Loading 0: 3%|▎ | 10/363 [00:00<00:13, 26.85it/s] Loading 0: 4%|▍ | 14/363 [00:00<00:14, 24.13it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:11, 30.31it/s] Loading 0: 6%|▋ | 23/363 [00:00<00:15, 22.09it/s] Loading 0: 7%|▋ | 26/363 [00:01<00:16, 19.87it/s] Loading 0: 9%|▉ | 32/363 [00:01<00:14, 22.79it/s] Loading 0: 10%|█ | 37/363 [00:01<00:11, 27.59it/s] Loading 0: 11%|█▏ | 41/363 [00:01<00:12, 24.93it/s] Loading 0: 13%|█▎ | 46/363 [00:01<00:11, 28.78it/s] Loading 0: 14%|█▍ | 50/363 [00:01<00:12, 25.69it/s] Loading 0: 15%|█▌ | 55/363 [00:02<00:10, 29.88it/s] Loading 0: 17%|█▋ | 60/363 [00:02<00:09, 30.82it/s] Loading 0: 18%|█▊ | 64/363 [00:02<00:14, 20.06it/s] Loading 0: 19%|█▉ | 69/363 [00:02<00:12, 24.44it/s] Loading 0: 20%|██ | 73/363 [00:02<00:12, 23.94it/s] Loading 0: 21%|██ | 77/363 [00:03<00:12, 22.04it/s] Loading 0: 23%|██▎ | 82/363 [00:03<00:10, 26.11it/s] Loading 0: 24%|██▎ | 86/363 [00:03<00:11, 23.40it/s] Loading 0: 26%|██▌ | 93/363 [00:03<00:09, 29.16it/s] Loading 0: 27%|██▋ | 97/363 [00:03<00:09, 27.64it/s] Loading 0: 28%|██▊ | 100/363 [00:03<00:09, 27.94it/s] Loading 0: 28%|██▊ | 103/363 [00:04<00:13, 19.07it/s] Loading 0: 29%|██▉ | 106/363 [00:04<00:13, 19.31it/s] Loading 0: 31%|███ | 111/363 [00:04<00:10, 23.02it/s] Loading 0: 31%|███▏ | 114/363 [00:04<00:11, 22.19it/s] Loading 0: 33%|███▎ | 120/363 [00:04<00:08, 27.34it/s] Loading 0: 34%|███▍ | 123/363 [00:04<00:09, 24.69it/s] Loading 0: 35%|███▍ | 127/363 [00:05<00:08, 27.43it/s] Loading 0: 36%|███▌ | 131/363 [00:05<00:09, 24.93it/s] Loading 0: 38%|███▊ | 137/363 [00:05<00:07, 29.56it/s] Loading 0: 39%|███▉ | 142/363 [00:05<00:08, 24.69it/s] Loading 0: 40%|███▉ | 145/363 [00:05<00:09, 23.60it/s] Loading 0: 41%|████ | 149/363 [00:06<00:09, 22.96it/s] Loading 0: 43%|████▎ | 156/363 [00:06<00:06, 29.69it/s] Loading 0: 44%|████▍ | 160/363 [00:06<00:07, 28.98it/s] Loading 0: 45%|████▌ | 165/363 [00:06<00:06, 31.53it/s] Loading 0: 47%|████▋ | 169/363 [00:06<00:06, 30.13it/s] Loading 0: 48%|████▊ | 174/363 [00:06<00:05, 31.71it/s] Loading 0: 49%|████▉ | 178/363 [00:06<00:06, 29.19it/s] Loading 0: 50%|█████ | 182/363 [00:07<00:07, 23.51it/s] Loading 0: 51%|█████ | 185/363 [00:07<00:09, 19.56it/s] Loading 0: 53%|█████▎ | 192/363 [00:07<00:06, 26.34it/s] Loading 0: 54%|█████▎ | 195/363 [00:07<00:06, 25.18it/s] Loading 0: 55%|█████▌ | 201/363 [00:07<00:05, 29.82it/s] Loading 0: 56%|█████▋ | 205/363 [00:07<00:05, 29.04it/s] Loading 0: 58%|█████▊ | 210/363 [00:08<00:04, 31.53it/s] Loading 0: 59%|█████▉ | 214/363 [00:08<00:04, 29.81it/s] Loading 0: 60%|██████ | 218/363 [00:08<00:04, 29.55it/s] Loading 0: 61%|██████▏ | 223/363 [00:08<00:05, 25.14it/s] Loading 0: 62%|██████▏ | 226/363 [00:08<00:06, 22.54it/s] Loading 0: 63%|██████▎ | 230/363 [00:09<00:06, 21.71it/s] Loading 0: 65%|██████▍ | 235/363 [00:09<00:04, 26.88it/s] Loading 0: 66%|██████▌ | 239/363 [00:09<00:05, 24.62it/s] Loading 0: 67%|██████▋ | 244/363 [00:09<00:04, 29.12it/s] Loading 0: 68%|██████▊ | 248/363 [00:09<00:04, 25.84it/s] Loading 0: 70%|██████▉ | 253/363 [00:09<00:03, 30.10it/s] Loading 0: 71%|███████ | 257/363 [00:09<00:03, 26.50it/s] Loading 0: 72%|███████▏ | 262/363 [00:10<00:03, 31.27it/s] Loading 0: 73%|███████▎ | 266/363 [00:10<00:04, 20.32it/s] Loading 0: 75%|███████▍ | 271/363 [00:10<00:03, 25.13it/s] Loading 0: 76%|███████▌ | 275/363 [00:10<00:03, 23.76it/s] Loading 0: 78%|███████▊ | 282/363 [00:10<00:02, 29.84it/s] Loading 0: 79%|███████▉ | 286/363 [00:11<00:02, 28.66it/s] Loading 0: 80%|████████ | 291/363 [00:11<00:02, 30.84it/s] Loading 0: 81%|████████▏ | 295/363 [00:11<00:02, 29.53it/s] Loading 0: 82%|████████▏ | 299/363 [00:11<00:02, 29.63it/s] Loading 0: 84%|████████▎ | 304/363 [00:11<00:02, 25.32it/s] Loading 0: 85%|████████▍ | 307/363 [00:11<00:02, 23.21it/s] Loading 0: 86%|████████▌ | 311/363 [00:12<00:02, 22.10it/s] Loading 0: 87%|████████▋ | 316/363 [00:12<00:01, 27.31it/s] Loading 0: 88%|████████▊ | 320/363 [00:12<00:01, 25.06it/s] Loading 0: 90%|█████████ | 327/363 [00:12<00:01, 31.51it/s] Loading 0: 91%|█████████ | 331/363 [00:12<00:01, 30.20it/s] Loading 0: 93%|█████████▎| 336/363 [00:12<00:00, 32.03it/s] Loading 0: 94%|█████████▎| 340/363 [00:12<00:00, 30.40it/s] Loading 0: 95%|█████████▍| 344/363 [00:19<00:09, 2.03it/s] Loading 0: 96%|█████████▌| 348/363 [00:20<00:05, 2.71it/s] Loading 0: 97%|█████████▋| 353/363 [00:20<00:02, 3.91it/s] Loading 0: 98%|█████████▊| 357/363 [00:20<00:01, 5.06it/s]
Job rirv938-rinen-grpo-40k-56847-v1-mkmlizer completed after 156.09s with status: succeeded
Stopping job with name rirv938-rinen-grpo-40k-56847-v1-mkmlizer
Pipeline stage MKMLizer completed in 156.81s
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-rinen-grpo-40k-56847-v1
Waiting for inference service rirv938-rinen-grpo-40k-56847-v1 to be ready
Inference service rirv938-rinen-grpo-40k-56847-v1 ready after 140.49469900131226s
Pipeline stage MKMLDeployer completed in 140.92s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8858282566070557s
Received healthy response to inference request in 1.571556568145752s
Received healthy response to inference request in 1.588456630706787s
Received healthy response to inference request in 1.702923059463501s
Received healthy response to inference request in 1.8009281158447266s
5 requests
0 failed requests
5th percentile: 1.574936580657959
10th percentile: 1.578316593170166
20th percentile: 1.5850766181945801
30th percentile: 1.61134991645813
40th percentile: 1.6571364879608155
50th percentile: 1.702923059463501
60th percentile: 1.7421250820159913
70th percentile: 1.7813271045684815
80th percentile: 1.8179081439971925
90th percentile: 1.851868200302124
95th percentile: 1.8688482284545898
99th percentile: 1.8824322509765625
mean time: 1.7099385261535645
Pipeline stage StressChecker completed in 9.91s
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 0.68s
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 0.72s
Shutdown handler de-registered
rirv938-rinen-grpo-40k-_56847_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5307.39s
Shutdown handler de-registered
rirv938-rinen-grpo-40k-_56847_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-rinen-grpo-40k-_56847_v1 status is now torndown due to DeploymentManager action