rirv938-grpo-to-compare_72853

developer_uid: rirv938

submission_id: rirv938-grpo-to-compare_72853_v2

model_name: rirv938-grpo-to-compare_72853_v2

model_group: rirv938/grpo_to_compare_

status: torndown

timestamp: 2025-04-26T01:00:43+00:00

num_battles: 10233

num_wins: 5856

celo_rating: 1349.98

family_friendly_score: 0.5294

family_friendly_standard_error: 0.0070588333313657435

submission_type: basic

model_repo: rirv938/grpo_to_compare_to_dpo_10k_cp312_lr6_merged

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.5298314680317201, 'latency_mean': 1.8873248851299287, 'latency_p50': 1.8916041851043701, 'latency_p90': 2.1028804540634156}, {'batch_size': 3, 'throughput': 1.0782136525010995, 'latency_mean': 2.7797209811210633, 'latency_p50': 2.765470504760742, 'latency_p90': 3.0610110282897947}, {'batch_size': 5, 'throughput': 1.4039043650065661, 'latency_mean': 3.5440945434570312, 'latency_p50': 3.549481987953186, 'latency_p90': 4.007516360282898}, {'batch_size': 6, 'throughput': 1.508450048194345, 'latency_mean': 3.941433970928192, 'latency_p50': 3.9511773586273193, 'latency_p90': 4.411201357841492}, {'batch_size': 8, 'throughput': 1.6416677460612996, 'latency_mean': 4.824749048948288, 'latency_p50': 4.805548429489136, 'latency_p90': 5.482922673225403}, {'batch_size': 10, 'throughput': 1.7533406101170124, 'latency_mean': 5.648687131404877, 'latency_p50': 5.604674577713013, 'latency_p90': 6.507300353050232}]

gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}

display_name: rirv938-grpo-to-compare_72853_v2

is_internal_developer: True

language_model: rirv938/grpo_to_compare_to_dpo_10k_cp312_lr6_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 1.46

us_pacific_date: 2025-04-25

win_ratio: 0.5722661975960129

generation_params: {'temperature': 0.9, 'top_p': 0.9, 'min_p': 0.2, 'top_k': 80, 'presence_penalty': 0.5, 'frequency_penalty': 0.5, 'stopping_words': ['</s>', '###', '\n', 'You:'], '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-grpo-to-compare-72853-v2-mkmlizer
Waiting for job on rirv938-grpo-to-compare-72853-v2-mkmlizer to finish
rirv938-grpo-to-compare-72853-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-grpo-to-compare-72853-v2-mkmlizer: ║     _____            __           __                                ║
rirv938-grpo-to-compare-72853-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-grpo-to-compare-72853-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-grpo-to-compare-72853-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-grpo-to-compare-72853-v2-mkmlizer: ║       /___/                                                         ║
rirv938-grpo-to-compare-72853-v2-mkmlizer: ║                                                                     ║
rirv938-grpo-to-compare-72853-v2-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-grpo-to-compare-72853-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-grpo-to-compare-72853-v2-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-grpo-to-compare-72853-v2-mkmlizer: ║                                                                     ║
rirv938-grpo-to-compare-72853-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-grpo-to-compare-72853-v2-mkmlizer: ║  belonging to:                                                      ║
rirv938-grpo-to-compare-72853-v2-mkmlizer: ║                                                                     ║
rirv938-grpo-to-compare-72853-v2-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-grpo-to-compare-72853-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-grpo-to-compare-72853-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-grpo-to-compare-72853-v2-mkmlizer: ║                                                                     ║
rirv938-grpo-to-compare-72853-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-grpo-to-compare-72853-v2-mkmlizer: Downloaded to shared memory in 191.429s
rirv938-grpo-to-compare-72853-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp4_xb4iq7, device:0
rirv938-grpo-to-compare-72853-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-grpo-to-compare-72853-v2-mkmlizer: quantized model in 64.530s
rirv938-grpo-to-compare-72853-v2-mkmlizer: Processed model rirv938/grpo_to_compare_to_dpo_10k_cp312_lr6_merged in 255.960s
rirv938-grpo-to-compare-72853-v2-mkmlizer: creating bucket guanaco-mkml-models
rirv938-grpo-to-compare-72853-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-grpo-to-compare-72853-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-grpo-to-compare-72853-v2
rirv938-grpo-to-compare-72853-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-grpo-to-compare-72853-v2/config.json
rirv938-grpo-to-compare-72853-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-grpo-to-compare-72853-v2/special_tokens_map.json
rirv938-grpo-to-compare-72853-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-grpo-to-compare-72853-v2/tokenizer_config.json
rirv938-grpo-to-compare-72853-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-grpo-to-compare-72853-v2/tokenizer.json
rirv938-grpo-to-compare-72853-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-grpo-to-compare-72853-v2/flywheel_model.1.safetensors
rirv938-grpo-to-compare-72853-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-grpo-to-compare-72853-v2/flywheel_model.0.safetensors
rirv938-grpo-to-compare-72853-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:12, 28.21it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:26, 13.49it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:16, 21.27it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:26, 13.13it/s]
Loading 0:   4%|▍         | 16/363 [00:01<00:27, 12.83it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:20, 16.59it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:25, 13.33it/s]
Loading 0:   8%|▊         | 29/363 [00:01<00:16, 20.83it/s]
Loading 0:   9%|▉         | 33/363 [00:01<00:17, 18.81it/s]
Loading 0:  10%|▉         | 36/363 [00:02<00:23, 14.13it/s]
Loading 0:  11%|█         | 39/363 [00:02<00:20, 16.17it/s]
Loading 0:  12%|█▏        | 42/363 [00:02<00:22, 14.34it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:17, 18.33it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:14, 22.29it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:19, 15.72it/s]
Loading 0:  15%|█▌        | 56/363 [00:03<00:18, 16.31it/s]
Loading 0:  16%|█▋        | 59/363 [00:03<00:24, 12.59it/s]
Loading 0:  18%|█▊        | 64/363 [00:03<00:16, 17.83it/s]
Loading 0:  19%|█▉        | 69/363 [00:04<00:15, 18.63it/s]
Loading 0:  20%|█▉        | 72/363 [00:04<00:20, 14.37it/s]
Loading 0:  21%|██        | 75/363 [00:04<00:17, 16.24it/s]
Loading 0:  21%|██▏       | 78/363 [00:04<00:19, 14.65it/s]
Loading 0:  23%|██▎       | 82/363 [00:04<00:15, 18.49it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:12, 21.43it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:17, 15.23it/s]
Loading 0:  25%|██▌       | 92/363 [00:05<00:17, 15.47it/s]
Loading 0:  27%|██▋       | 97/363 [00:05<00:12, 20.51it/s]
Loading 0:  28%|██▊       | 101/363 [00:05<00:12, 21.63it/s]
Loading 0:  29%|██▊       | 104/363 [00:06<00:14, 17.70it/s]
Loading 0:  29%|██▉       | 107/363 [00:06<00:18, 13.73it/s]
Loading 0:  30%|███       | 109/363 [00:06<00:19, 13.18it/s]
Loading 0:  31%|███       | 111/363 [00:06<00:18, 13.92it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:21, 11.61it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:13, 17.70it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:11, 21.34it/s]
Loading 0:  34%|███▍      | 125/363 [00:07<00:15, 15.29it/s]
Loading 0:  35%|███▌      | 128/363 [00:07<00:15, 15.62it/s]
Loading 0:  36%|███▌      | 130/363 [00:08<00:17, 13.70it/s]
Loading 0:  36%|███▋      | 132/363 [00:08<00:17, 12.94it/s]
Loading 0:  37%|███▋      | 136/363 [00:08<00:13, 17.28it/s]
Loading 0:  39%|███▊      | 140/363 [00:08<00:10, 21.32it/s]
Loading 0:  39%|███▉      | 143/363 [00:08<00:14, 15.14it/s]
Loading 0:  40%|████      | 146/363 [00:09<00:13, 15.80it/s]
Loading 0:  41%|████      | 148/363 [00:09<00:15, 13.85it/s]
Loading 0:  41%|████▏     | 150/363 [00:09<00:16, 13.20it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:11, 17.53it/s]
Loading 0:  44%|████▎     | 158/363 [00:09<00:09, 21.07it/s]
Loading 0:  44%|████▍     | 161/363 [00:09<00:13, 15.06it/s]
Loading 0:  45%|████▍     | 163/363 [00:10<00:14, 14.24it/s]
Loading 0:  45%|████▌     | 165/363 [00:10<00:13, 15.04it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:16, 11.95it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:10, 18.26it/s]
Loading 0:  48%|████▊     | 176/363 [00:10<00:08, 22.05it/s]
Loading 0:  49%|████▉     | 179/363 [00:11<00:11, 15.53it/s]
Loading 0:  50%|█████     | 182/363 [00:11<00:11, 16.20it/s]
Loading 0:  51%|█████     | 185/363 [00:11<00:14, 12.56it/s]
Loading 0:  53%|█████▎    | 191/363 [00:11<00:08, 19.21it/s]
Loading 0:  54%|█████▎    | 195/363 [00:11<00:09, 18.63it/s]
Loading 0:  55%|█████▍    | 198/363 [00:12<00:11, 14.31it/s]
Loading 0:  55%|█████▌    | 201/363 [00:27<03:35,  1.33s/it]
Loading 0:  56%|█████▌    | 203/363 [00:27<02:55,  1.10s/it]
Loading 0:  57%|█████▋    | 207/363 [00:27<01:50,  1.41it/s]
Loading 0:  58%|█████▊    | 210/363 [00:27<01:20,  1.90it/s]
Loading 0:  59%|█████▊    | 213/363 [00:28<01:01,  2.46it/s]
Loading 0:  59%|█████▉    | 215/363 [00:28<00:50,  2.93it/s]
Loading 0:  60%|█████▉    | 217/363 [00:28<00:41,  3.54it/s]
Loading 0:  60%|██████    | 219/363 [00:28<00:32,  4.44it/s]
Loading 0:  61%|██████    | 221/363 [00:28<00:28,  4.93it/s]
Loading 0:  62%|██████▏   | 226/363 [00:28<00:15,  8.57it/s]
Loading 0:  63%|██████▎   | 230/363 [00:29<00:11, 11.83it/s]
Loading 0:  64%|██████▍   | 233/363 [00:29<00:12, 10.73it/s]
Loading 0:  65%|██████▌   | 236/363 [00:29<00:10, 12.01it/s]
Loading 0:  66%|██████▌   | 238/363 [00:29<00:11, 11.22it/s]
Loading 0:  66%|██████▌   | 240/363 [00:29<00:11, 11.05it/s]
Loading 0:  67%|██████▋   | 244/363 [00:30<00:08, 14.81it/s]
Loading 0:  68%|██████▊   | 248/363 [00:30<00:06, 16.81it/s]
Loading 0:  69%|██████▉   | 251/363 [00:30<00:09, 11.84it/s]
Loading 0:  70%|██████▉   | 253/363 [00:30<00:09, 11.59it/s]
Loading 0:  70%|███████   | 255/363 [00:31<00:08, 12.52it/s]
Loading 0:  71%|███████   | 257/363 [00:31<00:09, 10.66it/s]
Loading 0:  72%|███████▏  | 262/363 [00:31<00:06, 16.57it/s]
Loading 0:  73%|███████▎  | 266/363 [00:31<00:04, 20.07it/s]
Loading 0:  74%|███████▍  | 269/363 [00:31<00:06, 14.19it/s]
Loading 0:  75%|███████▍  | 272/363 [00:32<00:06, 14.71it/s]
Loading 0:  75%|███████▌  | 274/363 [00:32<00:06, 13.20it/s]
Loading 0:  76%|███████▌  | 276/363 [00:32<00:06, 12.97it/s]
Loading 0:  77%|███████▋  | 280/363 [00:32<00:04, 17.56it/s]
Loading 0:  78%|███████▊  | 284/363 [00:32<00:03, 21.35it/s]
Loading 0:  79%|███████▉  | 287/363 [00:33<00:05, 14.98it/s]
Loading 0:  80%|███████▉  | 290/363 [00:33<00:04, 15.68it/s]
Loading 0:  80%|████████  | 292/363 [00:33<00:05, 13.82it/s]
Loading 0:  81%|████████  | 294/363 [00:33<00:05, 13.41it/s]
Loading 0:  82%|████████▏ | 298/363 [00:33<00:03, 17.91it/s]
Loading 0:  83%|████████▎ | 302/363 [00:33<00:02, 21.24it/s]
Loading 0:  84%|████████▍ | 305/363 [00:34<00:03, 14.79it/s]
Loading 0:  85%|████████▍ | 307/363 [00:34<00:04, 13.69it/s]
Loading 0:  85%|████████▌ | 309/363 [00:34<00:03, 14.43it/s]
Loading 0:  86%|████████▌ | 311/363 [00:34<00:04, 11.67it/s]
Loading 0:  87%|████████▋ | 316/363 [00:34<00:02, 17.77it/s]
Loading 0:  88%|████████▊ | 320/363 [00:35<00:02, 21.28it/s]
Loading 0:  89%|████████▉ | 323/363 [00:35<00:02, 15.02it/s]
Loading 0:  90%|████████▉ | 326/363 [00:35<00:02, 15.62it/s]
Loading 0:  90%|█████████ | 328/363 [00:35<00:02, 13.79it/s]
Loading 0:  91%|█████████ | 330/363 [00:35<00:02, 13.24it/s]
Loading 0:  92%|█████████▏| 334/363 [00:36<00:01, 17.31it/s]
Loading 0:  93%|█████████▎| 338/363 [00:36<00:01, 21.02it/s]
Loading 0:  94%|█████████▍| 341/363 [00:36<00:01, 14.96it/s]
Loading 0:  94%|█████████▍| 343/363 [00:36<00:01, 14.15it/s]
Loading 0:  95%|█████████▌| 345/363 [00:36<00:01, 14.77it/s]
Loading 0:  96%|█████████▌| 347/363 [00:37<00:01, 11.98it/s]
Loading 0:  97%|█████████▋| 352/363 [00:37<00:00, 17.98it/s]
Loading 0:  98%|█████████▊| 356/363 [00:37<00:00, 21.41it/s]
Loading 0:  99%|█████████▉| 359/363 [00:44<00:02,  1.47it/s]
Loading 0:  99%|█████████▉| 361/363 [00:44<00:01,  1.77it/s]
                                                            
Job rirv938-grpo-to-compare-72853-v2-mkmlizer completed after 288.84s with status: succeeded
Stopping job with name rirv938-grpo-to-compare-72853-v2-mkmlizer
Pipeline stage MKMLizer completed in 289.40s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-grpo-to-compare-72853-v2
Waiting for inference service rirv938-grpo-to-compare-72853-v2 to be ready
Inference service rirv938-grpo-to-compare-72853-v2 ready after 140.6230936050415s
Pipeline stage MKMLDeployer completed in 141.17s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.86547589302063s
Received healthy response to inference request in 2.044881820678711s
Received healthy response to inference request in 2.235830545425415s
Received healthy response to inference request in 2.0304243564605713s
Received healthy response to inference request in 1.8803918361663818s
5 requests
0 failed requests
5th percentile: 1.9103983402252198
10th percentile: 1.9404048442840576
20th percentile: 2.0004178524017333
30th percentile: 2.0333158493041994
40th percentile: 2.039098834991455
50th percentile: 2.044881820678711
60th percentile: 2.1212613105773928
70th percentile: 2.197640800476074
80th percentile: 2.361759614944458
90th percentile: 2.613617753982544
95th percentile: 2.7395468235015867
99th percentile: 2.840290079116821
mean time: 2.2114008903503417
Pipeline stage StressChecker completed in 12.64s
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 0.82s
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 0.83s
Shutdown handler de-registered
rirv938-grpo-to-compare_72853_v2 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 2771.07s
Shutdown handler de-registered
rirv938-grpo-to-compare_72853_v2 status is now inactive due to auto deactivation removed underperforming models
rirv938-grpo-to-compare_72853_v2 status is now torndown due to DeploymentManager action