rirv938-rinen-grpo-40k-c_7257

developer_uid: rirv938

submission_id: rirv938-rinen-grpo-40k-c_7257_v1

model_name: rirv938-rinen-grpo-40k-c_7257_v1

model_group: rirv938/rinen_grpo_40k_c

status: torndown

timestamp: 2025-05-15T15:51:09+00:00

num_battles: 8532

num_wins: 4278

celo_rating: 1290.71

family_friendly_score: 0.5332

family_friendly_standard_error: 0.00705546256456655

submission_type: basic

model_repo: rirv938/rinen_grpo_40k_cp444_95ff_run2_ww_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': 0.6022144743116635, 'latency_mean': 1.6604590404033661, 'latency_p50': 1.6650604009628296, 'latency_p90': 1.8293998003005982}, {'batch_size': 3, 'throughput': 1.0940562663552524, 'latency_mean': 2.7368169045448303, 'latency_p50': 2.7436163425445557, 'latency_p90': 3.0536003351211547}, {'batch_size': 5, 'throughput': 1.326781013794136, 'latency_mean': 3.758807691335678, 'latency_p50': 3.7476415634155273, 'latency_p90': 4.241501808166504}, {'batch_size': 6, 'throughput': 1.3794859974888203, 'latency_mean': 4.328757554292679, 'latency_p50': 4.333871841430664, 'latency_p90': 4.891342663764954}, {'batch_size': 8, 'throughput': 1.4599659296357173, 'latency_mean': 5.4252601397037505, 'latency_p50': 5.396973013877869, 'latency_p90': 6.1431679964065555}, {'batch_size': 10, 'throughput': 1.4956236957744482, 'latency_mean': 6.640685067176819, 'latency_p50': 6.63620924949646, 'latency_p90': 7.539459371566773}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rirv938-rinen-grpo-40k-c_7257_v1

is_internal_developer: True

language_model: rirv938/rinen_grpo_40k_cp444_95ff_run2_ww_merged

model_size: 13B

ranking_group: single

throughput_3p7s: 1.32

us_pacific_date: 2025-05-15

win_ratio: 0.5014064697609001

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', 'You:', '####', '<|im_end|>', '<|eot_id|>', 'Bot:', 'User:', '</s>'], '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-c-7257-v1-mkmlizer
Waiting for job on rirv938-rinen-grpo-40k-c-7257-v1-mkmlizer to finish
rirv938-rinen-grpo-40k-c-7257-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-rinen-grpo-40k-c-7257-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-rinen-grpo-40k-c-7257-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-rinen-grpo-40k-c-7257-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-rinen-grpo-40k-c-7257-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-rinen-grpo-40k-c-7257-v1-mkmlizer: ║       /___/                                                         ║
rirv938-rinen-grpo-40k-c-7257-v1-mkmlizer: ║                                                                     ║
rirv938-rinen-grpo-40k-c-7257-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-rinen-grpo-40k-c-7257-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-rinen-grpo-40k-c-7257-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-rinen-grpo-40k-c-7257-v1-mkmlizer: ║                                                                     ║
rirv938-rinen-grpo-40k-c-7257-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-rinen-grpo-40k-c-7257-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-rinen-grpo-40k-c-7257-v1-mkmlizer: ║                                                                     ║
rirv938-rinen-grpo-40k-c-7257-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-rinen-grpo-40k-c-7257-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-rinen-grpo-40k-c-7257-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-rinen-grpo-40k-c-7257-v1-mkmlizer: ║                                                                     ║
rirv938-rinen-grpo-40k-c-7257-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-rinen-grpo-40k-c-7257-v1-mkmlizer: Downloaded to shared memory in 83.237s
rirv938-rinen-grpo-40k-c-7257-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp6iz6x56o, device:0
rirv938-rinen-grpo-40k-c-7257-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-rinen-grpo-40k-c-7257-v1-mkmlizer: quantized model in 43.093s
rirv938-rinen-grpo-40k-c-7257-v1-mkmlizer: Processed model rirv938/rinen_grpo_40k_cp444_95ff_run2_ww_merged in 126.331s
rirv938-rinen-grpo-40k-c-7257-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-rinen-grpo-40k-c-7257-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-rinen-grpo-40k-c-7257-v1
rirv938-rinen-grpo-40k-c-7257-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-rinen-grpo-40k-c-7257-v1/special_tokens_map.json
rirv938-rinen-grpo-40k-c-7257-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-rinen-grpo-40k-c-7257-v1/config.json
rirv938-rinen-grpo-40k-c-7257-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-rinen-grpo-40k-c-7257-v1/tokenizer_config.json
rirv938-rinen-grpo-40k-c-7257-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-rinen-grpo-40k-c-7257-v1/tokenizer.json
rirv938-rinen-grpo-40k-c-7257-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-rinen-grpo-40k-c-7257-v1/flywheel_model.0.safetensors
rirv938-rinen-grpo-40k-c-7257-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 37.62it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:15, 22.62it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:14, 24.06it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:18, 18.63it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:13, 25.19it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:13, 25.88it/s]
Loading 0:   7%|▋         | 25/363 [00:01<00:19, 17.66it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:17, 18.78it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:17, 19.18it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:13, 24.79it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:14, 22.07it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:11, 26.69it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:13, 23.30it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:11, 27.55it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:10, 28.51it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:15, 18.88it/s]
Loading 0:  19%|█▉        | 69/363 [00:03<00:12, 23.23it/s]
Loading 0:  20%|██        | 73/363 [00:03<00:12, 23.63it/s]
Loading 0:  21%|██        | 77/363 [00:03<00:13, 21.85it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:10, 26.00it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:12, 22.16it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:10, 26.01it/s]
Loading 0:  26%|██▌       | 95/363 [00:04<00:11, 23.88it/s]
Loading 0:  28%|██▊       | 100/363 [00:04<00:09, 28.27it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:13, 18.66it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:11, 22.78it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:11, 20.93it/s]
Loading 0:  33%|███▎      | 118/363 [00:05<00:09, 25.07it/s]
Loading 0:  34%|███▎      | 122/363 [00:05<00:10, 22.11it/s]
Loading 0:  35%|███▍      | 127/363 [00:05<00:09, 26.08it/s]
Loading 0:  36%|███▌      | 131/363 [00:05<00:09, 23.43it/s]
Loading 0:  37%|███▋      | 136/363 [00:05<00:08, 27.43it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:07, 28.72it/s]
Loading 0:  40%|███▉      | 145/363 [00:06<00:10, 19.93it/s]
Loading 0:  41%|████      | 149/363 [00:06<00:10, 19.75it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:09, 23.14it/s]
Loading 0:  44%|████▎     | 158/363 [00:06<00:09, 21.53it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:07, 25.63it/s]
Loading 0:  46%|████▌     | 167/363 [00:07<00:08, 23.73it/s]
Loading 0:  47%|████▋     | 172/363 [00:07<00:06, 27.68it/s]
Loading 0:  48%|████▊     | 176/363 [00:07<00:07, 25.05it/s]
Loading 0:  50%|████▉     | 181/363 [00:07<00:06, 29.50it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:08, 19.85it/s]
Loading 0:  52%|█████▏    | 190/363 [00:08<00:06, 24.73it/s]
Loading 0:  53%|█████▎    | 194/363 [00:08<00:07, 22.80it/s]
Loading 0:  55%|█████▍    | 199/363 [00:08<00:06, 26.91it/s]
Loading 0:  56%|█████▌    | 203/363 [00:08<00:06, 24.17it/s]
Loading 0:  57%|█████▋    | 208/363 [00:08<00:05, 28.24it/s]
Loading 0:  58%|█████▊    | 212/363 [00:08<00:06, 24.96it/s]
Loading 0:  60%|█████▉    | 217/363 [00:09<00:05, 28.34it/s]
Loading 0:  61%|██████    | 222/363 [00:09<00:04, 28.69it/s]
Loading 0:  62%|██████▏   | 226/363 [00:09<00:06, 19.98it/s]
Loading 0:  63%|██████▎   | 230/363 [00:09<00:06, 19.67it/s]
Loading 0:  65%|██████▍   | 235/363 [00:09<00:05, 23.72it/s]
Loading 0:  66%|██████▌   | 238/363 [00:10<00:05, 24.67it/s]
Loading 0:  66%|██████▋   | 241/363 [00:10<00:05, 24.16it/s]
Loading 0:  68%|██████▊   | 246/363 [00:10<00:04, 26.63it/s]
Loading 0:  69%|██████▊   | 249/363 [00:10<00:04, 24.28it/s]
Loading 0:  70%|██████▉   | 253/363 [00:10<00:04, 27.27it/s]
Loading 0:  71%|███████   | 257/363 [00:10<00:04, 24.15it/s]
Loading 0:  72%|███████▏  | 262/363 [00:10<00:03, 27.06it/s]
Loading 0:  73%|███████▎  | 265/363 [00:11<00:05, 18.78it/s]
Loading 0:  74%|███████▍  | 268/363 [00:11<00:04, 19.83it/s]
Loading 0:  75%|███████▌  | 273/363 [00:11<00:03, 23.48it/s]
Loading 0:  76%|███████▌  | 276/363 [00:11<00:03, 22.28it/s]
Loading 0:  77%|███████▋  | 280/363 [00:11<00:03, 25.50it/s]
Loading 0:  78%|███████▊  | 284/363 [00:12<00:03, 23.11it/s]
Loading 0:  80%|███████▉  | 289/363 [00:12<00:02, 28.01it/s]
Loading 0:  81%|████████  | 293/363 [00:12<00:02, 24.69it/s]
Loading 0:  82%|████████▏ | 298/363 [00:12<00:02, 29.28it/s]
Loading 0:  83%|████████▎ | 303/363 [00:12<00:01, 30.44it/s]
Loading 0:  85%|████████▍ | 307/363 [00:12<00:02, 20.85it/s]
Loading 0:  86%|████████▌ | 311/363 [00:13<00:02, 20.43it/s]
Loading 0:  87%|████████▋ | 316/363 [00:13<00:01, 25.20it/s]
Loading 0:  88%|████████▊ | 320/363 [00:13<00:01, 23.37it/s]
Loading 0:  90%|████████▉ | 325/363 [00:13<00:01, 28.21it/s]
Loading 0:  91%|█████████ | 329/363 [00:13<00:01, 25.19it/s]
Loading 0:  92%|█████████▏| 334/363 [00:13<00:00, 29.81it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:00, 25.86it/s]
Loading 0:  94%|█████████▍| 343/363 [00:14<00:00, 30.57it/s]
Loading 0:  96%|█████████▌| 347/363 [00:21<00:07,  2.02it/s]
Loading 0:  96%|█████████▋| 350/363 [00:21<00:05,  2.55it/s]
Loading 0:  97%|█████████▋| 353/363 [00:21<00:03,  3.23it/s]
Loading 0:  98%|█████████▊| 357/363 [00:21<00:01,  4.43it/s]
                                                            
Job rirv938-rinen-grpo-40k-c-7257-v1-mkmlizer completed after 155.35s with status: succeeded
Stopping job with name rirv938-rinen-grpo-40k-c-7257-v1-mkmlizer
Pipeline stage MKMLizer completed in 155.90s
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-c-7257-v1
Waiting for inference service rirv938-rinen-grpo-40k-c-7257-v1 to be ready
Inference service rirv938-rinen-grpo-40k-c-7257-v1 ready after 130.54348301887512s
Pipeline stage MKMLDeployer completed in 131.12s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2852845191955566s
Received healthy response to inference request in 1.8599162101745605s
Received healthy response to inference request in 1.8356735706329346s
Received healthy response to inference request in 1.51271653175354s
Received healthy response to inference request in 1.6387872695922852s
5 requests
0 failed requests
5th percentile: 1.537930679321289
10th percentile: 1.563144826889038
20th percentile: 1.6135731220245362
30th percentile: 1.678164529800415
40th percentile: 1.7569190502166747
50th percentile: 1.8356735706329346
60th percentile: 1.845370626449585
70th percentile: 1.8550676822662353
80th percentile: 1.94498987197876
90th percentile: 2.1151371955871583
95th percentile: 2.2002108573913572
99th percentile: 2.2682697868347166
mean time: 1.8264756202697754
Pipeline stage StressChecker completed in 10.60s
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 0.89s
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 0.74s
Shutdown handler de-registered
rirv938-rinen-grpo-40k-c_7257_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 4736.54s
Shutdown handler de-registered
rirv938-rinen-grpo-40k-c_7257_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-rinen-grpo-40k-c_7257_v1 status is now torndown due to DeploymentManager action