rirv938-grpo-to-compare_34174

developer_uid: rirv938

submission_id: rirv938-grpo-to-compare_34174_v2

model_name: rirv938-grpo-to-compare_34174_v2

model_group: rirv938/grpo_to_compare_

status: torndown

timestamp: 2025-04-26T07:12:41+00:00

num_battles: 8713

num_wins: 4565

celo_rating: 1305.29

family_friendly_score: 0.5576

family_friendly_standard_error: 0.007023990888376778

submission_type: basic

model_repo: rirv938/grpo_to_compare_to_dpo_10k_cp312_lr8_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': 0.5298166834507686, 'latency_mean': 1.8873862195014954, 'latency_p50': 1.8864636421203613, 'latency_p90': 2.0998268127441406}, {'batch_size': 3, 'throughput': 1.0765090109092739, 'latency_mean': 2.7730398321151735, 'latency_p50': 2.7652673721313477, 'latency_p90': 3.050315260887146}, {'batch_size': 5, 'throughput': 1.3703060208834563, 'latency_mean': 3.6272444021701813, 'latency_p50': 3.6475411653518677, 'latency_p90': 4.069822931289673}, {'batch_size': 6, 'throughput': 1.4845949537326635, 'latency_mean': 4.001221274137497, 'latency_p50': 3.983733057975769, 'latency_p90': 4.477208638191223}, {'batch_size': 8, 'throughput': 1.6242171518368118, 'latency_mean': 4.878743349313736, 'latency_p50': 4.898752689361572, 'latency_p90': 5.482144069671631}, {'batch_size': 10, 'throughput': 1.7273531082904585, 'latency_mean': 5.745633594989776, 'latency_p50': 5.702373504638672, 'latency_p90': 6.5177661895751955}]

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

display_name: rirv938-grpo-to-compare_34174_v2

is_internal_developer: True

language_model: rirv938/grpo_to_compare_to_dpo_10k_cp312_lr8_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 1.4

us_pacific_date: 2025-04-26

win_ratio: 0.5239297601285435

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-34174-v2-mkmlizer
Waiting for job on rirv938-grpo-to-compare-34174-v2-mkmlizer to finish
rirv938-grpo-to-compare-34174-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-grpo-to-compare-34174-v2-mkmlizer: ║     _____            __           __                                ║
rirv938-grpo-to-compare-34174-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-grpo-to-compare-34174-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-grpo-to-compare-34174-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-grpo-to-compare-34174-v2-mkmlizer: ║       /___/                                                         ║
rirv938-grpo-to-compare-34174-v2-mkmlizer: ║                                                                     ║
rirv938-grpo-to-compare-34174-v2-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-grpo-to-compare-34174-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-grpo-to-compare-34174-v2-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-grpo-to-compare-34174-v2-mkmlizer: ║                                                                     ║
rirv938-grpo-to-compare-34174-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-grpo-to-compare-34174-v2-mkmlizer: ║  belonging to:                                                      ║
rirv938-grpo-to-compare-34174-v2-mkmlizer: ║                                                                     ║
rirv938-grpo-to-compare-34174-v2-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-grpo-to-compare-34174-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-grpo-to-compare-34174-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-grpo-to-compare-34174-v2-mkmlizer: ║                                                                     ║
rirv938-grpo-to-compare-34174-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-grpo-to-compare-34174-v2-mkmlizer: Downloaded to shared memory in 125.480s
rirv938-grpo-to-compare-34174-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp9isb0z6f, device:0
rirv938-grpo-to-compare-34174-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-grpo-to-compare-34174-v2-mkmlizer: quantized model in 63.135s
rirv938-grpo-to-compare-34174-v2-mkmlizer: Processed model rirv938/grpo_to_compare_to_dpo_10k_cp312_lr8_merged in 188.615s
rirv938-grpo-to-compare-34174-v2-mkmlizer: creating bucket guanaco-mkml-models
rirv938-grpo-to-compare-34174-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-grpo-to-compare-34174-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-grpo-to-compare-34174-v2
rirv938-grpo-to-compare-34174-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-grpo-to-compare-34174-v2/config.json
rirv938-grpo-to-compare-34174-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-grpo-to-compare-34174-v2/special_tokens_map.json
rirv938-grpo-to-compare-34174-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-grpo-to-compare-34174-v2/tokenizer_config.json
rirv938-grpo-to-compare-34174-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-grpo-to-compare-34174-v2/tokenizer.json
rirv938-grpo-to-compare-34174-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-grpo-to-compare-34174-v2/flywheel_model.1.safetensors
rirv938-grpo-to-compare-34174-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-grpo-to-compare-34174-v2/flywheel_model.0.safetensors
rirv938-grpo-to-compare-34174-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:12, 29.24it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:25, 14.08it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:15, 22.35it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:24, 14.07it/s]
Loading 0:   4%|▍         | 16/363 [00:01<00:25, 13.73it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:19, 17.30it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:24, 13.81it/s]
Loading 0:   8%|▊         | 29/363 [00:01<00:15, 21.44it/s]
Loading 0:   9%|▉         | 33/363 [00:01<00:16, 20.00it/s]
Loading 0:  10%|▉         | 36/363 [00:02<00:22, 14.49it/s]
Loading 0:  11%|█         | 39/363 [00:02<00:19, 16.49it/s]
Loading 0:  12%|█▏        | 42/363 [00:02<00:22, 14.57it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:17, 17.91it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:14, 21.25it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:20, 15.09it/s]
Loading 0:  15%|█▌        | 56/363 [00:03<00:19, 15.53it/s]
Loading 0:  16%|█▌        | 58/363 [00:03<00:22, 13.75it/s]
Loading 0:  17%|█▋        | 60/363 [00:03<00:23, 13.17it/s]
Loading 0:  18%|█▊        | 64/363 [00:03<00:17, 17.23it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:14, 20.96it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:19, 14.80it/s]
Loading 0:  20%|██        | 73/363 [00:04<00:20, 13.94it/s]
Loading 0:  21%|██        | 75/363 [00:04<00:19, 14.74it/s]
Loading 0:  21%|██        | 77/363 [00:04<00:23, 11.94it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:15, 18.53it/s]
Loading 0:  24%|██▍       | 87/363 [00:05<00:14, 19.16it/s]
Loading 0:  25%|██▍       | 90/363 [00:05<00:19, 14.25it/s]
Loading 0:  26%|██▋       | 96/363 [00:05<00:12, 20.88it/s]
Loading 0:  28%|██▊       | 101/363 [00:05<00:11, 22.35it/s]
Loading 0:  29%|██▊       | 104/363 [00:06<00:14, 18.48it/s]
Loading 0:  29%|██▉       | 107/363 [00:06<00:17, 14.43it/s]
Loading 0:  30%|███       | 109/363 [00:06<00:18, 13.93it/s]
Loading 0:  31%|███       | 111/363 [00:06<00:17, 14.62it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:20, 12.10it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:13, 18.13it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:10, 22.28it/s]
Loading 0:  34%|███▍      | 125/363 [00:07<00:15, 15.53it/s]
Loading 0:  35%|███▌      | 128/363 [00:07<00:14, 16.12it/s]
Loading 0:  36%|███▌      | 131/363 [00:08<00:18, 12.67it/s]
Loading 0:  37%|███▋      | 136/363 [00:08<00:12, 17.83it/s]
Loading 0:  39%|███▉      | 141/363 [00:08<00:11, 18.69it/s]
Loading 0:  40%|███▉      | 144/363 [00:08<00:15, 14.45it/s]
Loading 0:  40%|████      | 147/363 [00:08<00:13, 16.46it/s]
Loading 0:  41%|████▏     | 150/363 [00:09<00:14, 14.84it/s]
Loading 0:  43%|████▎     | 155/363 [00:09<00:10, 20.09it/s]
Loading 0:  44%|████▎     | 158/363 [00:09<00:09, 21.79it/s]
Loading 0:  44%|████▍     | 161/363 [00:09<00:13, 15.51it/s]
Loading 0:  45%|████▌     | 164/363 [00:09<00:12, 16.20it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:15, 12.73it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:10, 18.04it/s]
Loading 0:  48%|████▊     | 176/363 [00:10<00:08, 21.79it/s]
Loading 0:  50%|████▉     | 180/363 [00:11<00:13, 13.90it/s]
Loading 0:  50%|█████     | 183/363 [00:11<00:11, 15.86it/s]
Loading 0:  51%|█████     | 186/363 [00:11<00:12, 14.47it/s]
Loading 0:  52%|█████▏    | 190/363 [00:11<00:09, 18.24it/s]
Loading 0:  54%|█████▎    | 195/363 [00:11<00:08, 18.79it/s]
Loading 0:  55%|█████▍    | 198/363 [00:12<00:11, 14.32it/s]
Loading 0:  55%|█████▌    | 201/363 [00:26<03:33,  1.32s/it]
Loading 0:  56%|█████▌    | 203/363 [00:27<02:53,  1.09s/it]
Loading 0:  57%|█████▋    | 207/363 [00:27<01:49,  1.42it/s]
Loading 0:  58%|█████▊    | 210/363 [00:27<01:19,  1.92it/s]
Loading 0:  59%|█████▊    | 213/363 [00:27<00:59,  2.50it/s]
Loading 0:  59%|█████▉    | 215/363 [00:27<00:49,  2.98it/s]
Loading 0:  60%|█████▉    | 217/363 [00:28<00:40,  3.61it/s]
Loading 0:  60%|██████    | 219/363 [00:28<00:31,  4.53it/s]
Loading 0:  61%|██████    | 221/363 [00:28<00:28,  5.05it/s]
Loading 0:  62%|██████▏   | 226/363 [00:28<00:15,  8.85it/s]
Loading 0:  63%|██████▎   | 230/363 [00:28<00:11, 12.06it/s]
Loading 0:  64%|██████▍   | 233/363 [00:29<00:12, 10.77it/s]
Loading 0:  65%|██████▌   | 236/363 [00:29<00:10, 11.92it/s]
Loading 0:  66%|██████▌   | 238/363 [00:29<00:11, 11.35it/s]
Loading 0:  66%|██████▌   | 240/363 [00:29<00:10, 11.40it/s]
Loading 0:  67%|██████▋   | 244/363 [00:29<00:07, 15.76it/s]
Loading 0:  68%|██████▊   | 248/363 [00:29<00:05, 19.83it/s]
Loading 0:  69%|██████▉   | 251/363 [00:30<00:07, 14.38it/s]
Loading 0:  70%|██████▉   | 254/363 [00:30<00:07, 15.22it/s]
Loading 0:  71%|███████   | 256/363 [00:30<00:07, 13.54it/s]
Loading 0:  71%|███████   | 258/363 [00:30<00:07, 13.18it/s]
Loading 0:  72%|███████▏  | 262/363 [00:30<00:05, 17.76it/s]
Loading 0:  73%|███████▎  | 266/363 [00:30<00:04, 21.40it/s]
Loading 0:  74%|███████▍  | 269/363 [00:31<00:06, 15.07it/s]
Loading 0:  75%|███████▍  | 272/363 [00:31<00:05, 15.75it/s]
Loading 0:  75%|███████▌  | 274/363 [00:31<00:06, 13.95it/s]
Loading 0:  76%|███████▌  | 276/363 [00:31<00:06, 13.31it/s]
Loading 0:  77%|███████▋  | 280/363 [00:31<00:04, 17.80it/s]
Loading 0:  78%|███████▊  | 284/363 [00:32<00:03, 21.61it/s]
Loading 0:  79%|███████▉  | 287/363 [00:32<00:05, 15.03it/s]
Loading 0:  80%|███████▉  | 290/363 [00:32<00:04, 15.66it/s]
Loading 0:  80%|████████  | 292/363 [00:32<00:05, 13.85it/s]
Loading 0:  81%|████████  | 294/363 [00:32<00:05, 13.22it/s]
Loading 0:  82%|████████▏ | 298/363 [00:33<00:03, 17.39it/s]
Loading 0:  83%|████████▎ | 302/363 [00:33<00:02, 20.88it/s]
Loading 0:  84%|████████▍ | 305/363 [00:33<00:03, 14.59it/s]
Loading 0:  85%|████████▍ | 307/363 [00:33<00:04, 13.77it/s]
Loading 0:  85%|████████▌ | 309/363 [00:33<00:03, 14.68it/s]
Loading 0:  86%|████████▌ | 311/363 [00:34<00:04, 11.69it/s]
Loading 0:  87%|████████▋ | 316/363 [00:34<00:02, 17.64it/s]
Loading 0:  88%|████████▊ | 320/363 [00:34<00:02, 21.28it/s]
Loading 0:  89%|████████▉ | 323/363 [00:34<00:02, 14.91it/s]
Loading 0:  90%|████████▉ | 326/363 [00:34<00:02, 15.48it/s]
Loading 0:  90%|█████████ | 328/363 [00:35<00:02, 13.93it/s]
Loading 0:  91%|█████████ | 330/363 [00:35<00:02, 13.36it/s]
Loading 0:  92%|█████████▏| 334/363 [00:35<00:01, 17.80it/s]
Loading 0:  93%|█████████▎| 338/363 [00:35<00:01, 21.98it/s]
Loading 0:  94%|█████████▍| 341/363 [00:35<00:01, 15.76it/s]
Loading 0:  95%|█████████▍| 344/363 [00:36<00:01, 16.48it/s]
Loading 0:  96%|█████████▌| 347/363 [00:36<00:01, 12.87it/s]
Loading 0:  97%|█████████▋| 352/363 [00:36<00:00, 18.42it/s]
Loading 0:  98%|█████████▊| 356/363 [00:36<00:00, 22.04it/s]
Loading 0:  99%|█████████▉| 359/363 [00:43<00:02,  1.59it/s]
Loading 0: 100%|█████████▉| 362/363 [00:43<00:00,  2.06it/s]
                                                            
Job rirv938-grpo-to-compare-34174-v2-mkmlizer completed after 216.85s with status: succeeded
Stopping job with name rirv938-grpo-to-compare-34174-v2-mkmlizer
Pipeline stage MKMLizer completed in 217.33s
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-34174-v2
Waiting for inference service rirv938-grpo-to-compare-34174-v2 to be ready
Inference service rirv938-grpo-to-compare-34174-v2 ready after 130.46870017051697s
Pipeline stage MKMLDeployer completed in 130.97s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.785123586654663s
Received healthy response to inference request in 2.2702322006225586s
Received healthy response to inference request in 1.988464593887329s
Received healthy response to inference request in 2.364339590072632s
Received healthy response to inference request in 1.8594951629638672s
5 requests
0 failed requests
5th percentile: 1.8852890491485597
10th percentile: 1.911082935333252
20th percentile: 1.9626707077026366
30th percentile: 2.044818115234375
40th percentile: 2.157525157928467
50th percentile: 2.2702322006225586
60th percentile: 2.307875156402588
70th percentile: 2.345518112182617
80th percentile: 2.4484963893890384
90th percentile: 2.6168099880218505
95th percentile: 2.7009667873382566
99th percentile: 2.768292226791382
mean time: 2.25353102684021
Pipeline stage StressChecker completed in 12.57s
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 0.64s
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 0.67s
Shutdown handler de-registered
rirv938-grpo-to-compare_34174_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4542.58s
Shutdown handler de-registered
rirv938-grpo-to-compare_34174_v2 status is now inactive due to auto deactivation removed underperforming models
rirv938-grpo-to-compare_34174_v2 status is now torndown due to DeploymentManager action