rirv938-grpo-to-compare_87284

developer_uid: rirv938

submission_id: rirv938-grpo-to-compare_87284_v1

model_name: rirv938-grpo-to-compare_87284_v1

model_group: rirv938/grpo_to_compare_

status: torndown

timestamp: 2025-04-26T01:00:48+00:00

num_battles: 10625

num_wins: 5819

celo_rating: 1337.1

family_friendly_score: 0.5384

family_friendly_standard_error: 0.00705018354371005

submission_type: basic

model_repo: rirv938/grpo_to_compare_to_dpo_10k_cp156_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': 0.5297199509953879, 'latency_mean': 1.887718713283539, 'latency_p50': 1.8805862665176392, 'latency_p90': 2.0901855707168577}, {'batch_size': 3, 'throughput': 1.0849176323962577, 'latency_mean': 2.7570032978057863, 'latency_p50': 2.729348301887512, 'latency_p90': 3.0758307933807374}, {'batch_size': 5, 'throughput': 1.3943902149040075, 'latency_mean': 3.567079288959503, 'latency_p50': 3.569186210632324, 'latency_p90': 3.9536582708358763}, {'batch_size': 6, 'throughput': 1.5064233452346998, 'latency_mean': 3.958529284000397, 'latency_p50': 3.950164556503296, 'latency_p90': 4.4246098279953}, {'batch_size': 8, 'throughput': 1.664376961725035, 'latency_mean': 4.7793490254879, 'latency_p50': 4.766876697540283, 'latency_p90': 5.422146606445312}, {'batch_size': 10, 'throughput': 1.7466209223128695, 'latency_mean': 5.6838308417797085, 'latency_p50': 5.700880527496338, 'latency_p90': 6.45457398891449}]

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

display_name: rirv938-grpo-to-compare_87284_v1

is_internal_developer: True

language_model: rirv938/grpo_to_compare_to_dpo_10k_cp156_lr6_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 1.44

us_pacific_date: 2025-04-25

win_ratio: 0.5476705882352941

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>', 'You:', '\n', '###'], '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-87284-v1-mkmlizer
Waiting for job on rirv938-grpo-to-compare-87284-v1-mkmlizer to finish
rirv938-grpo-to-compare-87284-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-grpo-to-compare-87284-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-grpo-to-compare-87284-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-grpo-to-compare-87284-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-grpo-to-compare-87284-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-grpo-to-compare-87284-v1-mkmlizer: ║       /___/                                                         ║
rirv938-grpo-to-compare-87284-v1-mkmlizer: ║                                                                     ║
rirv938-grpo-to-compare-87284-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-grpo-to-compare-87284-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-grpo-to-compare-87284-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-grpo-to-compare-87284-v1-mkmlizer: ║                                                                     ║
rirv938-grpo-to-compare-87284-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-grpo-to-compare-87284-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-grpo-to-compare-87284-v1-mkmlizer: ║                                                                     ║
rirv938-grpo-to-compare-87284-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-grpo-to-compare-87284-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-grpo-to-compare-87284-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-grpo-to-compare-87284-v1-mkmlizer: ║                                                                     ║
rirv938-grpo-to-compare-87284-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-grpo-to-compare-87284-v1-mkmlizer: Downloaded to shared memory in 141.474s
rirv938-grpo-to-compare-87284-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpy4taamk5, device:0
rirv938-grpo-to-compare-87284-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-grpo-to-compare-87284-v1-mkmlizer: quantized model in 64.445s
rirv938-grpo-to-compare-87284-v1-mkmlizer: Processed model rirv938/grpo_to_compare_to_dpo_10k_cp156_lr6_merged in 205.919s
rirv938-grpo-to-compare-87284-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-grpo-to-compare-87284-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-grpo-to-compare-87284-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-grpo-to-compare-87284-v1
rirv938-grpo-to-compare-87284-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-grpo-to-compare-87284-v1/config.json
rirv938-grpo-to-compare-87284-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-grpo-to-compare-87284-v1/special_tokens_map.json
rirv938-grpo-to-compare-87284-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-grpo-to-compare-87284-v1/tokenizer_config.json
rirv938-grpo-to-compare-87284-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-grpo-to-compare-87284-v1/tokenizer.json
rirv938-grpo-to-compare-87284-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-grpo-to-compare-87284-v1/flywheel_model.1.safetensors
rirv938-grpo-to-compare-87284-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-grpo-to-compare-87284-v1/flywheel_model.0.safetensors
rirv938-grpo-to-compare-87284-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:12, 28.27it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:25, 13.86it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:16, 21.95it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:26, 13.37it/s]
Loading 0:   4%|▍         | 16/363 [00:01<00:26, 13.04it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:20, 16.88it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:25, 13.53it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:17, 19.61it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:14, 22.72it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:20, 15.64it/s]
Loading 0:  10%|█         | 38/363 [00:02<00:20, 16.16it/s]
Loading 0:  11%|█▏        | 41/363 [00:02<00:25, 12.47it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:18, 17.59it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:14, 21.18it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:20, 15.34it/s]
Loading 0:  15%|█▌        | 56/363 [00:03<00:19, 15.99it/s]
Loading 0:  16%|█▋        | 59/363 [00:03<00:24, 12.65it/s]
Loading 0:  18%|█▊        | 64/363 [00:03<00:16, 17.72it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:13, 21.31it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:19, 15.08it/s]
Loading 0:  20%|██        | 74/363 [00:04<00:18, 15.75it/s]
Loading 0:  21%|██        | 77/363 [00:04<00:23, 12.43it/s]
Loading 0:  23%|██▎       | 83/363 [00:05<00:14, 18.74it/s]
Loading 0:  24%|██▍       | 87/363 [00:05<00:15, 17.73it/s]
Loading 0:  25%|██▍       | 90/363 [00:05<00:19, 13.93it/s]
Loading 0:  26%|██▌       | 95/363 [00:05<00:14, 18.75it/s]
Loading 0:  27%|██▋       | 99/363 [00:05<00:11, 22.06it/s]
Loading 0:  28%|██▊       | 103/363 [00:06<00:15, 16.92it/s]
Loading 0:  29%|██▉       | 106/363 [00:06<00:16, 15.34it/s]
Loading 0:  30%|███       | 109/363 [00:06<00:18, 14.02it/s]
Loading 0:  31%|███       | 111/363 [00:06<00:17, 14.65it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:20, 12.10it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:13, 17.91it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:11, 21.81it/s]
Loading 0:  34%|███▍      | 125/363 [00:07<00:15, 15.41it/s]
Loading 0:  35%|███▌      | 128/363 [00:07<00:14, 15.74it/s]
Loading 0:  36%|███▌      | 131/363 [00:08<00:18, 12.21it/s]
Loading 0:  37%|███▋      | 136/363 [00:08<00:13, 16.90it/s]
Loading 0:  39%|███▊      | 140/363 [00:08<00:10, 20.29it/s]
Loading 0:  39%|███▉      | 143/363 [00:08<00:15, 14.61it/s]
Loading 0:  40%|████      | 146/363 [00:09<00:14, 14.99it/s]
Loading 0:  41%|████      | 148/363 [00:09<00:17, 12.49it/s]
Loading 0:  41%|████▏     | 150/363 [00:09<00:17, 12.18it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:12, 16.34it/s]
Loading 0:  44%|████▎     | 158/363 [00:09<00:10, 19.71it/s]
Loading 0:  44%|████▍     | 161/363 [00:10<00:14, 14.05it/s]
Loading 0:  45%|████▍     | 163/363 [00:10<00:14, 13.41it/s]
Loading 0:  45%|████▌     | 165/363 [00:10<00:14, 14.12it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:16, 11.53it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:10, 17.46it/s]
Loading 0:  48%|████▊     | 176/363 [00:10<00:08, 21.23it/s]
Loading 0:  49%|████▉     | 179/363 [00:11<00:12, 14.78it/s]
Loading 0:  50%|█████     | 182/363 [00:11<00:11, 15.60it/s]
Loading 0:  51%|█████     | 185/363 [00:11<00:14, 12.21it/s]
Loading 0:  52%|█████▏    | 190/363 [00:11<00:10, 17.24it/s]
Loading 0:  53%|█████▎    | 194/363 [00:12<00:08, 20.48it/s]
Loading 0:  54%|█████▍    | 197/363 [00:12<00:11, 14.90it/s]
Loading 0:  55%|█████▌    | 200/363 [00:12<00:10, 15.40it/s]
Loading 0:  56%|█████▌    | 203/363 [00:27<03:52,  1.45s/it]
Loading 0:  57%|█████▋    | 207/363 [00:28<02:30,  1.04it/s]
Loading 0:  58%|█████▊    | 210/363 [00:28<01:49,  1.40it/s]
Loading 0:  59%|█████▊    | 213/363 [00:28<01:21,  1.85it/s]
Loading 0:  60%|█████▉    | 216/363 [00:28<01:02,  2.36it/s]
Loading 0:  60%|██████    | 219/363 [00:28<00:44,  3.20it/s]
Loading 0:  61%|██████    | 221/363 [00:29<00:39,  3.62it/s]
Loading 0:  62%|██████▏   | 226/363 [00:29<00:22,  5.97it/s]
Loading 0:  63%|██████▎   | 230/363 [00:29<00:16,  8.15it/s]
Loading 0:  64%|██████▍   | 233/363 [00:29<00:15,  8.13it/s]
Loading 0:  65%|██████▍   | 235/363 [00:30<00:14,  8.66it/s]
Loading 0:  65%|██████▌   | 237/363 [00:30<00:12,  9.80it/s]
Loading 0:  66%|██████▌   | 239/363 [00:30<00:13,  9.10it/s]
Loading 0:  67%|██████▋   | 244/363 [00:30<00:08, 14.45it/s]
Loading 0:  68%|██████▊   | 248/363 [00:30<00:06, 18.30it/s]
Loading 0:  69%|██████▉   | 251/363 [00:30<00:08, 13.76it/s]
Loading 0:  70%|██████▉   | 254/363 [00:31<00:07, 14.62it/s]
Loading 0:  71%|███████   | 257/363 [00:31<00:08, 11.91it/s]
Loading 0:  72%|███████▏  | 262/363 [00:31<00:05, 17.05it/s]
Loading 0:  73%|███████▎  | 266/363 [00:31<00:04, 19.79it/s]
Loading 0:  74%|███████▍  | 269/363 [00:32<00:06, 14.90it/s]
Loading 0:  75%|███████▍  | 272/363 [00:32<00:05, 15.56it/s]
Loading 0:  76%|███████▌  | 275/363 [00:32<00:07, 12.29it/s]
Loading 0:  77%|███████▋  | 280/363 [00:32<00:04, 17.38it/s]
Loading 0:  78%|███████▊  | 284/363 [00:32<00:03, 20.59it/s]
Loading 0:  79%|███████▉  | 287/363 [00:33<00:05, 15.05it/s]
Loading 0:  80%|███████▉  | 290/363 [00:33<00:04, 15.64it/s]
Loading 0:  81%|████████  | 293/363 [00:33<00:05, 12.11it/s]
Loading 0:  82%|████████▏ | 298/363 [00:33<00:03, 16.86it/s]
Loading 0:  83%|████████▎ | 302/363 [00:34<00:03, 20.05it/s]
Loading 0:  84%|████████▍ | 305/363 [00:34<00:03, 14.86it/s]
Loading 0:  85%|████████▍ | 308/363 [00:34<00:03, 15.34it/s]
Loading 0:  86%|████████▌ | 311/363 [00:34<00:04, 12.19it/s]
Loading 0:  87%|████████▋ | 316/363 [00:35<00:02, 16.88it/s]
Loading 0:  88%|████████▊ | 320/363 [00:35<00:02, 20.42it/s]
Loading 0:  89%|████████▉ | 323/363 [00:35<00:02, 15.01it/s]
Loading 0:  90%|████████▉ | 326/363 [00:35<00:02, 15.60it/s]
Loading 0:  91%|█████████ | 329/363 [00:36<00:02, 12.37it/s]
Loading 0:  92%|█████████▏| 334/363 [00:36<00:01, 17.19it/s]
Loading 0:  93%|█████████▎| 338/363 [00:36<00:01, 20.39it/s]
Loading 0:  94%|█████████▍| 341/363 [00:36<00:01, 15.15it/s]
Loading 0:  95%|█████████▍| 344/363 [00:36<00:01, 15.81it/s]
Loading 0:  96%|█████████▌| 347/363 [00:37<00:01, 12.44it/s]
Loading 0:  97%|█████████▋| 352/363 [00:37<00:00, 17.56it/s]
Loading 0:  98%|█████████▊| 356/363 [00:37<00:00, 20.87it/s]
Loading 0:  99%|█████████▉| 359/363 [00:44<00:02,  1.59it/s]
Loading 0: 100%|█████████▉| 362/363 [00:44<00:00,  2.05it/s]
                                                            
Job rirv938-grpo-to-compare-87284-v1-mkmlizer completed after 236.84s with status: succeeded
Stopping job with name rirv938-grpo-to-compare-87284-v1-mkmlizer
Pipeline stage MKMLizer completed in 237.34s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-grpo-to-compare-87284-v1
Waiting for inference service rirv938-grpo-to-compare-87284-v1 to be ready
Unable to record family friendly update due to error: Invalid JSON input: JSON must contain 'User Safety' and 'Response Safety' fields
Inference service rirv938-grpo-to-compare-87284-v1 ready after 130.61094999313354s
Pipeline stage MKMLDeployer completed in 131.30s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6702640056610107s
Received healthy response to inference request in 2.112351894378662s
Received healthy response to inference request in 2.1025309562683105s
Received healthy response to inference request in 1.9964876174926758s
Received healthy response to inference request in 2.1737565994262695s
5 requests
0 failed requests
5th percentile: 2.0176962852478026
10th percentile: 2.0389049530029295
20th percentile: 2.0813222885131837
30th percentile: 2.104495143890381
40th percentile: 2.1084235191345213
50th percentile: 2.112351894378662
60th percentile: 2.136913776397705
70th percentile: 2.161475658416748
80th percentile: 2.2730580806732177
90th percentile: 2.4716610431671144
95th percentile: 2.5709625244140626
99th percentile: 2.6504037094116213
mean time: 2.2110782146453856
Pipeline stage StressChecker completed in 12.51s
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 0.65s
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 0.77s
Shutdown handler de-registered
rirv938-grpo-to-compare_87284_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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2764.98s
Shutdown handler de-registered
rirv938-grpo-to-compare_87284_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-grpo-to-compare_87284_v1 status is now torndown due to DeploymentManager action