rirv938-grpo-to-compare-_4371

developer_uid: rirv938

submission_id: rirv938-grpo-to-compare-_4371_v1

model_name: rirv938-grpo-to-compare-_4371_v1

model_group: rirv938/grpo_to_compare_

status: torndown

timestamp: 2025-04-25T23:59:56+00:00

num_battles: 10899

num_wins: 5471

celo_rating: 1289.75

family_friendly_score: 0.5486

family_friendly_standard_error: 0.007037585381364833

submission_type: basic

model_repo: rirv938/grpo_to_compare_to_dpo_10k_cp156_lr4_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': 0.5288293674741993, 'latency_mean': 1.8909021210670471, 'latency_p50': 1.8982737064361572, 'latency_p90': 2.106724667549133}, {'batch_size': 3, 'throughput': 1.0738024256291179, 'latency_mean': 2.789248135089874, 'latency_p50': 2.774110436439514, 'latency_p90': 3.0949331760406493}, {'batch_size': 5, 'throughput': 1.3658413155948936, 'latency_mean': 3.637333972454071, 'latency_p50': 3.6811457872390747, 'latency_p90': 4.083960676193238}, {'batch_size': 6, 'throughput': 1.4827435040824404, 'latency_mean': 4.021588099002838, 'latency_p50': 4.039180874824524, 'latency_p90': 4.534390497207641}, {'batch_size': 8, 'throughput': 1.600908019292078, 'latency_mean': 4.953770810365677, 'latency_p50': 4.964424133300781, 'latency_p90': 5.524335813522339}, {'batch_size': 10, 'throughput': 1.715811135031751, 'latency_mean': 5.797129681110382, 'latency_p50': 5.814202189445496, 'latency_p90': 6.542827367782593}]

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

display_name: rirv938-grpo-to-compare-_4371_v1

is_internal_developer: True

language_model: rirv938/grpo_to_compare_to_dpo_10k_cp156_lr4_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 1.4

us_pacific_date: 2025-04-25

win_ratio: 0.5019726580420222

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': ['\n', '</s>', '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-4371-v1-mkmlizer
Waiting for job on rirv938-grpo-to-compare-4371-v1-mkmlizer to finish
rirv938-grpo-to-compare-4371-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-grpo-to-compare-4371-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-grpo-to-compare-4371-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-grpo-to-compare-4371-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-grpo-to-compare-4371-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-grpo-to-compare-4371-v1-mkmlizer: ║       /___/                                                         ║
rirv938-grpo-to-compare-4371-v1-mkmlizer: ║                                                                     ║
rirv938-grpo-to-compare-4371-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-grpo-to-compare-4371-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-grpo-to-compare-4371-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-grpo-to-compare-4371-v1-mkmlizer: ║                                                                     ║
rirv938-grpo-to-compare-4371-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-grpo-to-compare-4371-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-grpo-to-compare-4371-v1-mkmlizer: ║                                                                     ║
rirv938-grpo-to-compare-4371-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-grpo-to-compare-4371-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-grpo-to-compare-4371-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-grpo-to-compare-4371-v1-mkmlizer: ║                                                                     ║
rirv938-grpo-to-compare-4371-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-grpo-to-compare-4371-v1-mkmlizer: Downloaded to shared memory in 169.250s
rirv938-grpo-to-compare-4371-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp16_v25t4, device:0
rirv938-grpo-to-compare-4371-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-grpo-to-compare-4371-v1-mkmlizer: quantized model in 65.023s
rirv938-grpo-to-compare-4371-v1-mkmlizer: Processed model rirv938/grpo_to_compare_to_dpo_10k_cp156_lr4_merged in 234.273s
rirv938-grpo-to-compare-4371-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-grpo-to-compare-4371-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-grpo-to-compare-4371-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-grpo-to-compare-4371-v1
rirv938-grpo-to-compare-4371-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-grpo-to-compare-4371-v1/config.json
rirv938-grpo-to-compare-4371-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-grpo-to-compare-4371-v1/special_tokens_map.json
rirv938-grpo-to-compare-4371-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-grpo-to-compare-4371-v1/tokenizer_config.json
rirv938-grpo-to-compare-4371-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-grpo-to-compare-4371-v1/tokenizer.json
rirv938-grpo-to-compare-4371-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-grpo-to-compare-4371-v1/flywheel_model.1.safetensors
rirv938-grpo-to-compare-4371-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-grpo-to-compare-4371-v1/flywheel_model.0.safetensors
rirv938-grpo-to-compare-4371-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:13, 27.18it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:26, 13.36it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:17, 20.70it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:26, 13.27it/s]
Loading 0:   4%|▍         | 16/363 [00:01<00:27, 12.67it/s]
Loading 0:   5%|▌         | 19/363 [00:01<00:21, 15.67it/s]
Loading 0:   6%|▌         | 22/363 [00:01<00:22, 14.95it/s]
Loading 0:   7%|▋         | 24/363 [00:01<00:24, 13.80it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:18, 17.79it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:15, 21.28it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:22, 14.34it/s]
Loading 0:  10%|█         | 37/363 [00:02<00:24, 13.26it/s]
Loading 0:  11%|█         | 39/363 [00:02<00:23, 13.91it/s]
Loading 0:  11%|█▏        | 41/363 [00:02<00:28, 11.28it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:18, 17.02it/s]
Loading 0:  14%|█▍        | 50/363 [00:03<00:15, 20.44it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:21, 14.55it/s]
Loading 0:  15%|█▌        | 55/363 [00:03<00:22, 13.58it/s]
Loading 0:  16%|█▌        | 57/363 [00:03<00:21, 14.18it/s]
Loading 0:  16%|█▋        | 59/363 [00:04<00:27, 11.21it/s]
Loading 0:  18%|█▊        | 64/363 [00:04<00:17, 16.94it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:14, 20.49it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:20, 14.49it/s]
Loading 0:  20%|██        | 74/363 [00:04<00:19, 15.03it/s]
Loading 0:  21%|██        | 76/363 [00:05<00:21, 13.35it/s]
Loading 0:  21%|██▏       | 78/363 [00:05<00:22, 12.80it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:16, 17.06it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:13, 20.63it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:19, 14.08it/s]
Loading 0:  25%|██▌       | 91/363 [00:06<00:20, 13.19it/s]
Loading 0:  26%|██▌       | 95/363 [00:06<00:15, 17.20it/s]
Loading 0:  27%|██▋       | 99/363 [00:06<00:12, 20.98it/s]
Loading 0:  28%|██▊       | 102/363 [00:06<00:13, 19.22it/s]
Loading 0:  29%|██▉       | 105/363 [00:06<00:17, 14.84it/s]
Loading 0:  29%|██▉       | 107/363 [00:07<00:18, 13.48it/s]
Loading 0:  30%|███       | 109/363 [00:07<00:19, 12.76it/s]
Loading 0:  31%|███       | 111/363 [00:07<00:18, 13.63it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:22, 11.00it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:14, 17.17it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:11, 20.84it/s]
Loading 0:  34%|███▍      | 125/363 [00:08<00:16, 14.85it/s]
Loading 0:  35%|███▌      | 128/363 [00:08<00:15, 15.34it/s]
Loading 0:  36%|███▌      | 130/363 [00:08<00:17, 13.57it/s]
Loading 0:  36%|███▋      | 132/363 [00:08<00:17, 13.31it/s]
Loading 0:  37%|███▋      | 136/363 [00:08<00:12, 18.09it/s]
Loading 0:  39%|███▉      | 141/363 [00:09<00:11, 18.92it/s]
Loading 0:  40%|███▉      | 144/363 [00:09<00:15, 13.90it/s]
Loading 0:  40%|████      | 147/363 [00:09<00:13, 16.02it/s]
Loading 0:  41%|████▏     | 150/363 [00:09<00:14, 14.44it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:11, 18.05it/s]
Loading 0:  44%|████▎     | 158/363 [00:10<00:09, 21.79it/s]
Loading 0:  44%|████▍     | 161/363 [00:10<00:12, 15.54it/s]
Loading 0:  45%|████▌     | 164/363 [00:10<00:12, 15.94it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:15, 12.45it/s]
Loading 0:  47%|████▋     | 172/363 [00:11<00:10, 17.65it/s]
Loading 0:  48%|████▊     | 176/363 [00:11<00:08, 21.36it/s]
Loading 0:  49%|████▉     | 179/363 [00:11<00:11, 15.46it/s]
Loading 0:  50%|█████     | 182/363 [00:11<00:11, 15.96it/s]
Loading 0:  51%|█████     | 185/363 [00:12<00:14, 12.54it/s]
Loading 0:  52%|█████▏    | 190/363 [00:12<00:09, 17.58it/s]
Loading 0:  53%|█████▎    | 194/363 [00:12<00:07, 21.17it/s]
Loading 0:  54%|█████▍    | 197/363 [00:12<00:10, 15.47it/s]
Loading 0:  55%|█████▌    | 200/363 [00:12<00:10, 16.15it/s]
Loading 0:  56%|█████▌    | 203/363 [00:28<03:50,  1.44s/it]
Loading 0:  57%|█████▋    | 207/363 [00:28<02:29,  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 [00:29<01:02,  2.36it/s]
Loading 0:  60%|██████    | 219/363 [00:29<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,  5.99it/s]
Loading 0:  63%|██████▎   | 230/363 [00:29<00:16,  8.20it/s]
Loading 0:  64%|██████▍   | 233/363 [00:30<00:15,  8.19it/s]
Loading 0:  65%|██████▌   | 236/363 [00:30<00:13,  9.55it/s]
Loading 0:  66%|██████▌   | 238/363 [00:30<00:13,  9.55it/s]
Loading 0:  66%|██████▌   | 240/363 [00:30<00:12,  9.88it/s]
Loading 0:  67%|██████▋   | 244/363 [00:30<00:08, 13.60it/s]
Loading 0:  68%|██████▊   | 248/363 [00:30<00:06, 17.05it/s]
Loading 0:  69%|██████▉   | 251/363 [00:31<00:08, 12.97it/s]
Loading 0:  70%|██████▉   | 253/363 [00:31<00:08, 12.53it/s]
Loading 0:  70%|███████   | 255/363 [00:31<00:08, 13.30it/s]
Loading 0:  71%|███████   | 257/363 [00:31<00:09, 11.00it/s]
Loading 0:  72%|███████▏  | 262/363 [00:31<00:06, 16.54it/s]
Loading 0:  73%|███████▎  | 266/363 [00:32<00:04, 19.96it/s]
Loading 0:  74%|███████▍  | 269/363 [00:32<00:06, 14.42it/s]
Loading 0:  75%|███████▍  | 271/363 [00:32<00:06, 13.59it/s]
Loading 0:  75%|███████▌  | 273/363 [00:32<00:06, 14.49it/s]
Loading 0:  76%|███████▌  | 275/363 [00:32<00:07, 11.75it/s]
Loading 0:  77%|███████▋  | 280/363 [00:33<00:04, 17.77it/s]
Loading 0:  78%|███████▊  | 284/363 [00:33<00:03, 21.05it/s]
Loading 0:  79%|███████▉  | 287/363 [00:33<00:05, 15.00it/s]
Loading 0:  80%|███████▉  | 290/363 [00:33<00:04, 15.59it/s]
Loading 0:  80%|████████  | 292/363 [00:33<00:05, 13.67it/s]
Loading 0:  81%|████████  | 294/363 [00:34<00:05, 13.40it/s]
Loading 0:  82%|████████▏ | 298/363 [00:34<00:03, 18.12it/s]
Loading 0:  83%|████████▎ | 302/363 [00:34<00:02, 22.36it/s]
Loading 0:  84%|████████▍ | 305/363 [00:34<00:03, 14.97it/s]
Loading 0:  85%|████████▍ | 308/363 [00:34<00:03, 15.76it/s]
Loading 0:  86%|████████▌ | 311/363 [00:35<00:04, 12.58it/s]
Loading 0:  87%|████████▋ | 316/363 [00:35<00:02, 18.07it/s]
Loading 0:  88%|████████▊ | 320/363 [00:35<00:01, 21.87it/s]
Loading 0:  89%|████████▉ | 324/363 [00:35<00:02, 13.80it/s]
Loading 0:  90%|█████████ | 327/363 [00:36<00:02, 15.80it/s]
Loading 0:  91%|█████████ | 330/363 [00:36<00:02, 14.60it/s]
Loading 0:  92%|█████████▏| 335/363 [00:36<00:01, 19.77it/s]
Loading 0:  93%|█████████▎| 339/363 [00:36<00:01, 18.97it/s]
Loading 0:  94%|█████████▍| 342/363 [00:37<00:01, 14.43it/s]
Loading 0:  95%|█████████▌| 345/363 [00:37<00:01, 16.56it/s]
Loading 0:  96%|█████████▌| 348/363 [00:37<00:01, 14.91it/s]
Loading 0:  97%|█████████▋| 353/363 [00:37<00:00, 20.37it/s]
Loading 0:  98%|█████████▊| 357/363 [00:44<00:03,  1.72it/s]
Loading 0:  99%|█████████▉| 360/363 [00:44<00:01,  2.20it/s]
Loading 0: 100%|█████████▉| 362/363 [00:44<00:00,  2.62it/s]
                                                            
Job rirv938-grpo-to-compare-4371-v1-mkmlizer completed after 269.19s with status: succeeded
Stopping job with name rirv938-grpo-to-compare-4371-v1-mkmlizer
Pipeline stage MKMLizer completed in 269.72s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-grpo-to-compare-4371-v1
Waiting for inference service rirv938-grpo-to-compare-4371-v1 to be ready
Inference service rirv938-grpo-to-compare-4371-v1 ready after 140.49266457557678s
Pipeline stage MKMLDeployer completed in 141.04s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.305964946746826s
Received healthy response to inference request in 1.8806400299072266s
Received healthy response to inference request in 2.097673177719116s
Received healthy response to inference request in 1.9797790050506592s
Received healthy response to inference request in 2.0660483837127686s
5 requests
0 failed requests
5th percentile: 1.900467824935913
10th percentile: 1.9202956199645995
20th percentile: 1.9599512100219727
30th percentile: 1.997032880783081
40th percentile: 2.031540632247925
50th percentile: 2.0660483837127686
60th percentile: 2.0786983013153075
70th percentile: 2.0913482189178465
80th percentile: 2.1393315315246584
90th percentile: 2.2226482391357423
95th percentile: 2.264306592941284
99th percentile: 2.2976332759857176
mean time: 2.0660211086273192
Pipeline stage StressChecker completed in 11.71s
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 0.63s
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-grpo-to-compare-_4371_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 3024.91s
Shutdown handler de-registered
rirv938-grpo-to-compare-_4371_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-grpo-to-compare-_4371_v1 status is now torndown due to DeploymentManager action