rirv938-grpo-to-compare_97129

developer_uid: rirv938

submission_id: rirv938-grpo-to-compare_97129_v1

model_name: rirv938-grpo-to-compare_97129_v1

model_group: rirv938/grpo_to_compare_

status: torndown

timestamp: 2025-04-28T18:49:06+00:00

num_battles: 8880

num_wins: 4632

celo_rating: 1305.67

family_friendly_score: 0.573

family_friendly_standard_error: 0.006995298421082549

submission_type: basic

model_repo: rirv938/grpo_to_compare_to_dpo_10k_cp156_with_ff_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': 0.5260624741543428, 'latency_mean': 1.9008587765693665, 'latency_p50': 1.9277470111846924, 'latency_p90': 2.114159846305847}, {'batch_size': 3, 'throughput': 1.0864962778614013, 'latency_mean': 2.7565659463405607, 'latency_p50': 2.752401351928711, 'latency_p90': 3.027222919464111}, {'batch_size': 5, 'throughput': 1.4066066618354538, 'latency_mean': 3.536596952676773, 'latency_p50': 3.5378401279449463, 'latency_p90': 3.9984535932540894}, {'batch_size': 6, 'throughput': 1.5087073414624523, 'latency_mean': 3.952006132602692, 'latency_p50': 3.971833109855652, 'latency_p90': 4.384320688247681}, {'batch_size': 8, 'throughput': 1.675181836715174, 'latency_mean': 4.742237509489059, 'latency_p50': 4.700473427772522, 'latency_p90': 5.369680500030517}, {'batch_size': 10, 'throughput': 1.7511458861825984, 'latency_mean': 5.666289489269257, 'latency_p50': 5.639786005020142, 'latency_p90': 6.4381523609161375}]

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

display_name: rirv938-grpo-to-compare_97129_v1

is_internal_developer: True

language_model: rirv938/grpo_to_compare_to_dpo_10k_cp156_with_ff_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 1.46

us_pacific_date: 2025-04-28

win_ratio: 0.5216216216216216

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': ['You:', '</s>', '\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-97129-v1-mkmlizer
Waiting for job on rirv938-grpo-to-compare-97129-v1-mkmlizer to finish
rirv938-grpo-to-compare-97129-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-grpo-to-compare-97129-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-grpo-to-compare-97129-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-grpo-to-compare-97129-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-grpo-to-compare-97129-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-grpo-to-compare-97129-v1-mkmlizer: ║       /___/                                                         ║
rirv938-grpo-to-compare-97129-v1-mkmlizer: ║                                                                     ║
rirv938-grpo-to-compare-97129-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-grpo-to-compare-97129-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-grpo-to-compare-97129-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-grpo-to-compare-97129-v1-mkmlizer: ║                                                                     ║
rirv938-grpo-to-compare-97129-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-grpo-to-compare-97129-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-grpo-to-compare-97129-v1-mkmlizer: ║                                                                     ║
rirv938-grpo-to-compare-97129-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-grpo-to-compare-97129-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-grpo-to-compare-97129-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-grpo-to-compare-97129-v1-mkmlizer: ║                                                                     ║
rirv938-grpo-to-compare-97129-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-grpo-to-compare-97129-v1-mkmlizer: Downloaded to shared memory in 164.345s
rirv938-grpo-to-compare-97129-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpi3_w7ybb, device:0
rirv938-grpo-to-compare-97129-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-grpo-to-compare-97129-v1-mkmlizer: quantized model in 76.714s
rirv938-grpo-to-compare-97129-v1-mkmlizer: Processed model rirv938/grpo_to_compare_to_dpo_10k_cp156_with_ff_merged in 241.060s
rirv938-grpo-to-compare-97129-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-grpo-to-compare-97129-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-grpo-to-compare-97129-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-grpo-to-compare-97129-v1
rirv938-grpo-to-compare-97129-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-grpo-to-compare-97129-v1/config.json
rirv938-grpo-to-compare-97129-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-grpo-to-compare-97129-v1/special_tokens_map.json
rirv938-grpo-to-compare-97129-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-grpo-to-compare-97129-v1/tokenizer_config.json
rirv938-grpo-to-compare-97129-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-grpo-to-compare-97129-v1/tokenizer.json
rirv938-grpo-to-compare-97129-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-grpo-to-compare-97129-v1/flywheel_model.1.safetensors
rirv938-grpo-to-compare-97129-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-grpo-to-compare-97129-v1/flywheel_model.0.safetensors
rirv938-grpo-to-compare-97129-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:18, 19.45it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:34, 10.44it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:16, 21.15it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:24, 14.27it/s]
Loading 0:   4%|▍         | 16/363 [00:01<00:25, 13.67it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:19, 17.14it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:24, 13.76it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:17, 19.67it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:14, 22.56it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:21, 15.17it/s]
Loading 0:  10%|█         | 38/363 [00:02<00:20, 15.95it/s]
Loading 0:  11%|█▏        | 41/363 [00:02<00:25, 12.78it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:17, 17.84it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:14, 21.25it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:20, 15.24it/s]
Loading 0:  15%|█▌        | 56/363 [00:03<00:19, 15.59it/s]
Loading 0:  16%|█▋        | 59/363 [00:03<00:24, 12.50it/s]
Loading 0:  18%|█▊        | 64/363 [00:03<00:17, 17.30it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:14, 20.24it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:19, 14.62it/s]
Loading 0:  20%|██        | 74/363 [00:04<00:18, 15.26it/s]
Loading 0:  21%|██        | 77/363 [00:04<00:23, 12.11it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:16, 16.76it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:14, 19.78it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:18, 14.57it/s]
Loading 0:  25%|██▌       | 92/363 [00:05<00:17, 15.07it/s]
Loading 0:  26%|██▌       | 95/363 [00:05<00:15, 17.28it/s]
Loading 0:  27%|██▋       | 99/363 [00:06<00:12, 20.93it/s]
Loading 0:  28%|██▊       | 102/363 [00:06<00:13, 19.22it/s]
Loading 0:  29%|██▉       | 105/363 [00:06<00:17, 14.44it/s]
Loading 0:  29%|██▉       | 107/363 [00:06<00:19, 13.45it/s]
Loading 0:  30%|███       | 109/363 [00:06<00:19, 13.01it/s]
Loading 0:  31%|███       | 111/363 [00:07<00:18, 13.94it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:22, 11.31it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:14, 17.30it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:11, 20.87it/s]
Loading 0:  34%|███▍      | 125/363 [00:07<00:16, 14.67it/s]
Loading 0:  35%|███▍      | 127/363 [00:08<00:16, 13.99it/s]
Loading 0:  36%|███▌      | 129/363 [00:08<00:15, 14.87it/s]
Loading 0:  36%|███▌      | 131/363 [00:08<00:19, 11.86it/s]
Loading 0:  37%|███▋      | 136/363 [00:08<00:12, 17.77it/s]
Loading 0:  39%|███▊      | 140/363 [00:08<00:10, 21.23it/s]
Loading 0:  39%|███▉      | 143/363 [00:09<00:14, 14.74it/s]
Loading 0:  40%|████      | 146/363 [00:09<00:13, 15.53it/s]
Loading 0:  41%|████      | 148/363 [00:09<00:15, 13.82it/s]
Loading 0:  41%|████▏     | 150/363 [00:09<00:16, 13.28it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:12, 17.34it/s]
Loading 0:  44%|████▎     | 158/363 [00:09<00:09, 21.09it/s]
Loading 0:  44%|████▍     | 161/363 [00:10<00:13, 14.89it/s]
Loading 0:  45%|████▍     | 163/363 [00:10<00:14, 14.13it/s]
Loading 0:  45%|████▌     | 165/363 [00:10<00:13, 15.03it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:16, 12.07it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:10, 17.92it/s]
Loading 0:  48%|████▊     | 176/363 [00:10<00:08, 21.43it/s]
Loading 0:  49%|████▉     | 179/363 [00:11<00:12, 14.89it/s]
Loading 0:  50%|█████     | 182/363 [00:11<00:11, 15.68it/s]
Loading 0:  51%|█████     | 184/363 [00:11<00:12, 14.07it/s]
Loading 0:  51%|█████     | 186/363 [00:11<00:13, 13.37it/s]
Loading 0:  52%|█████▏    | 190/363 [00:11<00:09, 17.53it/s]
Loading 0:  53%|█████▎    | 194/363 [00:12<00:08, 21.06it/s]
Loading 0:  54%|█████▍    | 197/363 [00:12<00:11, 14.74it/s]
Loading 0:  55%|█████▍    | 199/363 [00:12<00:11, 14.06it/s]
Loading 0:  55%|█████▌    | 200/363 [00:32<00:11, 14.06it/s]
Loading 0:  55%|█████▌    | 201/363 [00:32<06:23,  2.37s/it]
Loading 0:  56%|█████▌    | 203/363 [00:32<04:50,  1.82s/it]
Loading 0:  57%|█████▋    | 207/363 [00:33<02:47,  1.07s/it]
Loading 0:  58%|█████▊    | 210/363 [00:33<01:55,  1.32it/s]
Loading 0:  59%|█████▊    | 213/363 [00:33<01:23,  1.80it/s]
Loading 0:  59%|█████▉    | 215/363 [00:33<01:06,  2.21it/s]
Loading 0:  60%|█████▉    | 217/363 [00:33<00:52,  2.77it/s]
Loading 0:  60%|██████    | 219/363 [00:33<00:40,  3.55it/s]
Loading 0:  61%|██████    | 221/363 [00:34<00:34,  4.16it/s]
Loading 0:  62%|██████▏   | 226/363 [00:34<00:18,  7.48it/s]
Loading 0:  63%|██████▎   | 230/363 [00:34<00:12, 10.39it/s]
Loading 0:  64%|██████▍   | 233/363 [00:34<00:13,  9.77it/s]
Loading 0:  65%|██████▌   | 236/363 [00:34<00:11, 11.26it/s]
Loading 0:  66%|██████▌   | 239/363 [00:35<00:12, 10.22it/s]
Loading 0:  67%|██████▋   | 244/363 [00:35<00:08, 14.79it/s]
Loading 0:  68%|██████▊   | 248/363 [00:35<00:06, 18.03it/s]
Loading 0:  69%|██████▉   | 251/363 [00:35<00:08, 13.74it/s]
Loading 0:  70%|██████▉   | 254/363 [00:36<00:07, 14.67it/s]
Loading 0:  71%|███████   | 257/363 [00:36<00:08, 12.14it/s]
Loading 0:  72%|███████▏  | 262/363 [00:36<00:06, 16.64it/s]
Loading 0:  73%|███████▎  | 266/363 [00:36<00:04, 19.68it/s]
Loading 0:  74%|███████▍  | 269/363 [00:37<00:06, 14.67it/s]
Loading 0:  75%|███████▍  | 272/363 [00:37<00:05, 15.51it/s]
Loading 0:  76%|███████▌  | 275/363 [00:37<00:07, 12.34it/s]
Loading 0:  77%|███████▋  | 280/363 [00:37<00:04, 17.05it/s]
Loading 0:  78%|███████▊  | 284/363 [00:37<00:03, 20.00it/s]
Loading 0:  79%|███████▉  | 287/363 [00:38<00:05, 14.74it/s]
Loading 0:  80%|███████▉  | 290/363 [00:38<00:04, 15.49it/s]
Loading 0:  81%|████████  | 293/363 [00:38<00:05, 12.47it/s]
Loading 0:  82%|████████▏ | 298/363 [00:38<00:03, 17.25it/s]
Loading 0:  83%|████████▎ | 302/363 [00:38<00:03, 20.19it/s]
Loading 0:  84%|████████▍ | 305/363 [00:39<00:03, 14.81it/s]
Loading 0:  85%|████████▍ | 308/363 [00:39<00:03, 15.47it/s]
Loading 0:  86%|████████▌ | 311/363 [00:39<00:04, 12.47it/s]
Loading 0:  87%|████████▋ | 316/363 [00:39<00:02, 17.24it/s]
Loading 0:  88%|████████▊ | 320/363 [00:40<00:02, 20.20it/s]
Loading 0:  89%|████████▉ | 323/363 [00:40<00:02, 14.89it/s]
Loading 0:  90%|████████▉ | 326/363 [00:40<00:02, 15.59it/s]
Loading 0:  91%|█████████ | 329/363 [00:41<00:02, 12.54it/s]
Loading 0:  92%|█████████▏| 334/363 [00:41<00:01, 17.37it/s]
Loading 0:  93%|█████████▎| 338/363 [00:41<00:01, 20.35it/s]
Loading 0:  94%|█████████▍| 341/363 [00:41<00:01, 14.97it/s]
Loading 0:  95%|█████████▍| 344/363 [00:41<00:01, 15.67it/s]
Loading 0:  96%|█████████▌| 347/363 [00:42<00:01, 12.59it/s]
Loading 0:  97%|█████████▋| 352/363 [00:42<00:00, 17.30it/s]
Loading 0:  98%|█████████▊| 356/363 [00:42<00:00, 20.24it/s]
Loading 0:  99%|█████████▉| 359/363 [00:50<00:02,  1.46it/s]
Loading 0:  99%|█████████▉| 361/363 [00:50<00:01,  1.73it/s]
                                                            
Job rirv938-grpo-to-compare-97129-v1-mkmlizer completed after 270.22s with status: succeeded
Stopping job with name rirv938-grpo-to-compare-97129-v1-mkmlizer
Pipeline stage MKMLizer completed in 270.69s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-grpo-to-compare-97129-v1
Waiting for inference service rirv938-grpo-to-compare-97129-v1 to be ready
Failed to get response for submission chaiml-damien-mafia-bos_79245_v2: HTTPConnectionPool(host='chaiml-damien-mafia-bos-79245-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-damien-mafia-bos_79245_v2: HTTPConnectionPool(host='chaiml-damien-mafia-bos-79245-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service rirv938-grpo-to-compare-97129-v1 ready after 130.48073363304138s
Pipeline stage MKMLDeployer completed in 130.93s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4456686973571777s
Received healthy response to inference request in 2.1097359657287598s
Received healthy response to inference request in 1.957273244857788s
Received healthy response to inference request in 1.8340823650360107s
Received healthy response to inference request in 1.8715944290161133s
5 requests
0 failed requests
5th percentile: 1.8415847778320313
10th percentile: 1.8490871906280517
20th percentile: 1.8640920162200927
30th percentile: 1.8887301921844482
40th percentile: 1.9230017185211181
50th percentile: 1.957273244857788
60th percentile: 2.0182583332061768
70th percentile: 2.0792434215545654
80th percentile: 2.1769225120544435
90th percentile: 2.3112956047058106
95th percentile: 2.378482151031494
99th percentile: 2.432231388092041
mean time: 2.0436709403991697
Pipeline stage StressChecker completed in 11.47s
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 0.71s
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 0.65s
Shutdown handler de-registered
rirv938-grpo-to-compare_97129_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 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-grpo-to-compare-97129-v1-profiler
Waiting for inference service rirv938-grpo-to-compare-97129-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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2907.89s
Shutdown handler de-registered
rirv938-grpo-to-compare_97129_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-grpo-to-compare_97129_v1 status is now torndown due to DeploymentManager action