chaiml-rinen-grpo-40k-c_60950

developer_uid: rirv938

submission_id: chaiml-rinen-grpo-40k-c_60950_v1

model_name: chaiml-rinen-grpo-40k-c_60950_v1

model_group: ChaiML/rinen_grpo_40k_cp

status: torndown

timestamp: 2025-05-01T18:44:31+00:00

num_battles: 8424

num_wins: 4475

celo_rating: 1329.19

family_friendly_score: 0.5691999999999999

family_friendly_standard_error: 0.0070030187776415394

submission_type: basic

model_repo: ChaiML/rinen_grpo_40k_cp1184_95ff

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': 0.598768348828337, 'latency_mean': 1.670015196800232, 'latency_p50': 1.6728154420852661, 'latency_p90': 1.8375649213790894}, {'batch_size': 3, 'throughput': 1.1178106172721542, 'latency_mean': 2.676811052560806, 'latency_p50': 2.6676918268203735, 'latency_p90': 2.9791309595108033}, {'batch_size': 5, 'throughput': 1.319897820816412, 'latency_mean': 3.768078989982605, 'latency_p50': 3.7886626720428467, 'latency_p90': 4.248992919921875}, {'batch_size': 6, 'throughput': 1.4072683450052201, 'latency_mean': 4.246350739002228, 'latency_p50': 4.251952409744263, 'latency_p90': 4.7318902015686035}, {'batch_size': 8, 'throughput': 1.474806944612898, 'latency_mean': 5.376544080972671, 'latency_p50': 5.3591355085372925, 'latency_p90': 5.988091230392456}, {'batch_size': 10, 'throughput': 1.5140946098205683, 'latency_mean': 6.55130735874176, 'latency_p50': 6.541160821914673, 'latency_p90': 7.382930731773376}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-rinen-grpo-40k-c_60950_v1

is_internal_developer: True

language_model: ChaiML/rinen_grpo_40k_cp1184_95ff

model_size: 13B

ranking_group: single

throughput_3p7s: 1.32

us_pacific_date: 2025-05-01

win_ratio: 0.5312203228869895

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': ['Bot:', 'User:', '\n', '</s>', '####', '<|im_end|>', '<|eot_id|>', 'You:'], '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 chaiml-rinen-grpo-40k-c-60950-v1-mkmlizer
Waiting for job on chaiml-rinen-grpo-40k-c-60950-v1-mkmlizer to finish
chaiml-rinen-grpo-40k-c-60950-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-rinen-grpo-40k-c-60950-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-rinen-grpo-40k-c-60950-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-rinen-grpo-40k-c-60950-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-rinen-grpo-40k-c-60950-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-rinen-grpo-40k-c-60950-v1-mkmlizer: ║       /___/                                                         ║
chaiml-rinen-grpo-40k-c-60950-v1-mkmlizer: ║                                                                     ║
chaiml-rinen-grpo-40k-c-60950-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-rinen-grpo-40k-c-60950-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-rinen-grpo-40k-c-60950-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-rinen-grpo-40k-c-60950-v1-mkmlizer: ║                                                                     ║
chaiml-rinen-grpo-40k-c-60950-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-rinen-grpo-40k-c-60950-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-rinen-grpo-40k-c-60950-v1-mkmlizer: ║                                                                     ║
chaiml-rinen-grpo-40k-c-60950-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-rinen-grpo-40k-c-60950-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-rinen-grpo-40k-c-60950-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-rinen-grpo-40k-c-60950-v1-mkmlizer: ║                                                                     ║
chaiml-rinen-grpo-40k-c-60950-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission chaiml-anthropic-grpo-4_66492_v1: HTTPConnectionPool(host='chaiml-anthropic-grpo-4-66492-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-rinen-grpo-40k-c-60950-v1-mkmlizer: Downloaded to shared memory in 66.915s
chaiml-rinen-grpo-40k-c-60950-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpa3qykvko, device:0
chaiml-rinen-grpo-40k-c-60950-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-rinen-grpo-40k-c-60950-v1-mkmlizer: quantized model in 40.744s
chaiml-rinen-grpo-40k-c-60950-v1-mkmlizer: Processed model ChaiML/rinen_grpo_40k_cp1184_95ff in 107.659s
chaiml-rinen-grpo-40k-c-60950-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-rinen-grpo-40k-c-60950-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-rinen-grpo-40k-c-60950-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-rinen-grpo-40k-c-60950-v1
chaiml-rinen-grpo-40k-c-60950-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-rinen-grpo-40k-c-60950-v1/config.json
chaiml-rinen-grpo-40k-c-60950-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-rinen-grpo-40k-c-60950-v1/special_tokens_map.json
chaiml-rinen-grpo-40k-c-60950-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-rinen-grpo-40k-c-60950-v1/tokenizer_config.json
chaiml-rinen-grpo-40k-c-60950-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-rinen-grpo-40k-c-60950-v1/tokenizer.json
chaiml-rinen-grpo-40k-c-60950-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-rinen-grpo-40k-c-60950-v1/flywheel_model.0.safetensors
chaiml-rinen-grpo-40k-c-60950-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 22.01it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 28.21it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:13, 25.51it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:09, 37.12it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:15, 22.00it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:13, 24.45it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:10, 30.65it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:10, 30.03it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 32.57it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 30.64it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:10, 30.67it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 26.66it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:12, 23.19it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:09, 30.40it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:10, 28.60it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 27.42it/s]
Loading 0:  23%|██▎       | 84/363 [00:02<00:09, 30.30it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:09, 29.16it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:08, 31.57it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:08, 30.05it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:10, 24.43it/s]
Loading 0:  29%|██▊       | 104/363 [00:03<00:11, 21.60it/s]
Loading 0:  30%|███       | 109/363 [00:03<00:09, 26.96it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:10, 24.23it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:07, 30.94it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 29.27it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 31.53it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 30.18it/s]
Loading 0:  38%|███▊      | 137/363 [00:04<00:07, 30.34it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 25.63it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:08, 24.27it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:09, 23.59it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:06, 30.34it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:06, 29.55it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 32.47it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 31.51it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:05, 33.78it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:05, 30.85it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 24.77it/s]
Loading 0:  51%|█████     | 185/363 [00:06<00:08, 21.75it/s]
Loading 0:  53%|█████▎    | 192/363 [00:06<00:05, 29.22it/s]
Loading 0:  54%|█████▍    | 196/363 [00:06<00:05, 28.72it/s]
Loading 0:  55%|█████▌    | 201/363 [00:07<00:05, 31.52it/s]
Loading 0:  56%|█████▋    | 205/363 [00:07<00:05, 30.71it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:04, 33.47it/s]
Loading 0:  59%|█████▉    | 214/363 [00:07<00:04, 31.32it/s]
Loading 0:  60%|██████    | 218/363 [00:07<00:04, 31.68it/s]
Loading 0:  61%|██████▏   | 223/363 [00:07<00:05, 27.36it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:05, 25.42it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:05, 23.90it/s]
Loading 0:  65%|██████▌   | 237/363 [00:08<00:04, 30.29it/s]
Loading 0:  66%|██████▋   | 241/363 [00:08<00:04, 28.87it/s]
Loading 0:  68%|██████▊   | 246/363 [00:08<00:03, 30.77it/s]
Loading 0:  69%|██████▉   | 250/363 [00:08<00:03, 29.29it/s]
Loading 0:  70%|███████   | 255/363 [00:08<00:03, 31.93it/s]
Loading 0:  71%|███████▏  | 259/363 [00:09<00:03, 30.66it/s]
Loading 0:  72%|███████▏  | 263/363 [00:09<00:03, 25.07it/s]
Loading 0:  73%|███████▎  | 266/363 [00:09<00:04, 22.04it/s]
Loading 0:  75%|███████▌  | 273/363 [00:09<00:03, 29.46it/s]
Loading 0:  76%|███████▋  | 277/363 [00:09<00:03, 27.89it/s]
Loading 0:  78%|███████▊  | 282/363 [00:09<00:02, 30.30it/s]
Loading 0:  79%|███████▉  | 286/363 [00:10<00:02, 30.06it/s]
Loading 0:  80%|████████  | 291/363 [00:10<00:02, 32.28it/s]
Loading 0:  81%|████████▏ | 295/363 [00:10<00:02, 30.91it/s]
Loading 0:  82%|████████▏ | 299/363 [00:10<00:02, 31.30it/s]
Loading 0:  84%|████████▎ | 304/363 [00:10<00:02, 27.39it/s]
Loading 0:  85%|████████▍ | 307/363 [00:10<00:02, 25.59it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 23.85it/s]
Loading 0:  88%|████████▊ | 318/363 [00:11<00:01, 30.56it/s]
Loading 0:  89%|████████▊ | 322/363 [00:11<00:01, 30.28it/s]
Loading 0:  90%|█████████ | 327/363 [00:11<00:01, 33.03it/s]
Loading 0:  91%|█████████ | 331/363 [00:11<00:01, 31.20it/s]
Loading 0:  93%|█████████▎| 336/363 [00:11<00:00, 33.94it/s]
Loading 0:  94%|█████████▎| 340/363 [00:11<00:00, 32.13it/s]
Loading 0:  95%|█████████▍| 344/363 [00:18<00:09,  2.00it/s]
Loading 0:  96%|█████████▌| 348/363 [00:18<00:05,  2.68it/s]
Loading 0:  97%|█████████▋| 353/363 [00:19<00:02,  3.90it/s]
Loading 0:  98%|█████████▊| 357/363 [00:19<00:01,  5.06it/s]
                                                            
Job chaiml-rinen-grpo-40k-c-60950-v1-mkmlizer completed after 135.61s with status: succeeded
Stopping job with name chaiml-rinen-grpo-40k-c-60950-v1-mkmlizer
Pipeline stage MKMLizer completed in 136.37s
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 chaiml-rinen-grpo-40k-c-60950-v1
Waiting for inference service chaiml-rinen-grpo-40k-c-60950-v1 to be ready
Failed to get response for submission chaiml-anthropic-grpo-4_77013_v1: HTTPConnectionPool(host='chaiml-anthropic-grpo-4-77013-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-anthropic-grpo-4_77013_v1: HTTPConnectionPool(host='chaiml-anthropic-grpo-4-77013-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-anthropic-grpo-4_66492_v2: HTTPConnectionPool(host='chaiml-anthropic-grpo-4-66492-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service chaiml-rinen-grpo-40k-c-60950-v1 ready after 150.47937393188477s
Pipeline stage MKMLDeployer completed in 150.94s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.4865870475769043s
Received healthy response to inference request in 1.6882202625274658s
Received healthy response to inference request in 1.660982608795166s
Received healthy response to inference request in 1.7180204391479492s
5 requests
1 failed requests
5th percentile: 1.6664301395416259
10th percentile: 1.671877670288086
20th percentile: 1.682772731781006
30th percentile: 1.6941802978515625
40th percentile: 1.7061003684997558
50th percentile: 1.7180204391479492
60th percentile: 2.0254470825195314
70th percentile: 2.332873725891113
80th percentile: 6.018379735946658
90th percentile: 13.08196511268616
95th percentile: 16.613757801055904
99th percentile: 19.43919195175171
mean time: 5.539872169494629
%s, retrying in %s seconds...
Received healthy response to inference request in 1.5157501697540283s
Received healthy response to inference request in 1.6820995807647705s
Received healthy response to inference request in 1.5913538932800293s
Received healthy response to inference request in 1.906369924545288s
Received healthy response to inference request in 1.7447338104248047s
5 requests
0 failed requests
5th percentile: 1.5308709144592285
10th percentile: 1.5459916591644287
20th percentile: 1.576233148574829
30th percentile: 1.6095030307769775
40th percentile: 1.645801305770874
50th percentile: 1.6820995807647705
60th percentile: 1.7071532726287841
70th percentile: 1.7322069644927978
80th percentile: 1.7770610332489014
90th percentile: 1.8417154788970946
95th percentile: 1.8740427017211914
99th percentile: 1.8999044799804687
mean time: 1.6880614757537842
Pipeline stage StressChecker completed in 38.75s
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 0.70s
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
chaiml-rinen-grpo-40k-c_60950_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 0.14s
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 chaiml-rinen-grpo-40k-c-60950-v1-profiler
Waiting for inference service chaiml-rinen-grpo-40k-c-60950-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5092.68s
Shutdown handler de-registered
chaiml-rinen-grpo-40k-c_60950_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-rinen-grpo-40k-c_60950_v1 status is now torndown due to DeploymentManager action