rirv938-grpo-to-compare_75170

developer_uid: rirv938

submission_id: rirv938-grpo-to-compare_75170_v1

model_name: rirv938-grpo-to-compare_75170_v1

model_group: rirv938/grpo_to_compare_

status: torndown

timestamp: 2025-04-25T17:30:51+00:00

num_battles: 6931

num_wins: 3507

celo_rating: 1286.57

family_friendly_score: 0.5654

family_friendly_standard_error: 0.007010318680345424

submission_type: basic

model_repo: rirv938/grpo_to_compare_to_dpo_10k_cp310_lr2_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': 0.5321259211515699, 'latency_mean': 1.879199048280716, 'latency_p50': 1.8840405941009521, 'latency_p90': 2.0942514419555662}, {'batch_size': 3, 'throughput': 1.0781963946471331, 'latency_mean': 2.7747791957855226, 'latency_p50': 2.7935067415237427, 'latency_p90': 3.064631581306457}, {'batch_size': 5, 'throughput': 1.3990211104355819, 'latency_mean': 3.559793039560318, 'latency_p50': 3.5955252647399902, 'latency_p90': 4.022883129119873}, {'batch_size': 6, 'throughput': 1.5209947370796493, 'latency_mean': 3.912541493177414, 'latency_p50': 3.907099962234497, 'latency_p90': 4.427171063423157}, {'batch_size': 8, 'throughput': 1.6408919026705602, 'latency_mean': 4.831511157751083, 'latency_p50': 4.824469208717346, 'latency_p90': 5.464462542533875}, {'batch_size': 10, 'throughput': 1.7514557064297955, 'latency_mean': 5.645430510044098, 'latency_p50': 5.607871055603027, 'latency_p90': 6.507391333580017}]

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

display_name: rirv938-grpo-to-compare_75170_v1

is_internal_developer: True

language_model: rirv938/grpo_to_compare_to_dpo_10k_cp310_lr2_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 1.46

us_pacific_date: 2025-04-25

win_ratio: 0.5059875919780695

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-75170-v1-mkmlizer
Waiting for job on rirv938-grpo-to-compare-75170-v1-mkmlizer to finish
rirv938-grpo-to-compare-75170-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-grpo-to-compare-75170-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-grpo-to-compare-75170-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-grpo-to-compare-75170-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-grpo-to-compare-75170-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-grpo-to-compare-75170-v1-mkmlizer: ║       /___/                                                         ║
rirv938-grpo-to-compare-75170-v1-mkmlizer: ║                                                                     ║
rirv938-grpo-to-compare-75170-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-grpo-to-compare-75170-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-grpo-to-compare-75170-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-grpo-to-compare-75170-v1-mkmlizer: ║                                                                     ║
rirv938-grpo-to-compare-75170-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-grpo-to-compare-75170-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-grpo-to-compare-75170-v1-mkmlizer: ║                                                                     ║
rirv938-grpo-to-compare-75170-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-grpo-to-compare-75170-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-grpo-to-compare-75170-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-grpo-to-compare-75170-v1-mkmlizer: ║                                                                     ║
rirv938-grpo-to-compare-75170-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-grpo-to-compare-75170-v1-mkmlizer: Downloaded to shared memory in 164.401s
rirv938-grpo-to-compare-75170-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpqntj2i_m, device:0
rirv938-grpo-to-compare-75170-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-grpo-to-compare-75170-v1-mkmlizer: quantized model in 64.846s
rirv938-grpo-to-compare-75170-v1-mkmlizer: Processed model rirv938/grpo_to_compare_to_dpo_10k_cp310_lr2_merged in 229.247s
rirv938-grpo-to-compare-75170-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-grpo-to-compare-75170-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-grpo-to-compare-75170-v1/config.json
rirv938-grpo-to-compare-75170-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-grpo-to-compare-75170-v1/special_tokens_map.json
rirv938-grpo-to-compare-75170-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-grpo-to-compare-75170-v1/tokenizer_config.json
rirv938-grpo-to-compare-75170-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-grpo-to-compare-75170-v1/tokenizer.json
rirv938-grpo-to-compare-75170-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-grpo-to-compare-75170-v1/flywheel_model.1.safetensors
rirv938-grpo-to-compare-75170-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-grpo-to-compare-75170-v1/flywheel_model.0.safetensors
rirv938-grpo-to-compare-75170-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:14, 24.66it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:26, 13.53it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:17, 20.59it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:25, 13.97it/s]
Loading 0:   4%|▍         | 15/363 [00:01<00:29, 11.63it/s]
Loading 0:   5%|▌         | 19/363 [00:01<00:20, 16.49it/s]
Loading 0:   6%|▌         | 22/363 [00:01<00:22, 15.46it/s]
Loading 0:   7%|▋         | 25/363 [00:01<00:21, 15.86it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:18, 18.36it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:15, 21.86it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:22, 14.73it/s]
Loading 0:  10%|█         | 37/363 [00:02<00:23, 13.93it/s]
Loading 0:  11%|█         | 39/363 [00:02<00:21, 14.74it/s]
Loading 0:  11%|█▏        | 41/363 [00:02<00:27, 11.78it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:17, 17.65it/s]
Loading 0:  14%|█▍        | 50/363 [00:03<00:14, 20.93it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:21, 14.75it/s]
Loading 0:  15%|█▌        | 56/363 [00:03<00:19, 15.63it/s]
Loading 0:  16%|█▌        | 58/363 [00:03<00:22, 13.79it/s]
Loading 0:  17%|█▋        | 60/363 [00:03<00:23, 13.10it/s]
Loading 0:  18%|█▊        | 64/363 [00:04<00:17, 17.19it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:14, 20.78it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:20, 14.59it/s]
Loading 0:  20%|██        | 73/363 [00:04<00:20, 13.94it/s]
Loading 0:  21%|██        | 75/363 [00:04<00:19, 14.59it/s]
Loading 0:  21%|██        | 77/363 [00:05<00:24, 11.58it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:16, 17.32it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:13, 20.61it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:20, 13.57it/s]
Loading 0:  25%|██▌       | 91/363 [00:05<00:22, 12.31it/s]
Loading 0:  26%|██▌       | 95/363 [00:06<00:16, 16.08it/s]
Loading 0:  27%|██▋       | 99/363 [00:06<00:13, 19.46it/s]
Loading 0:  28%|██▊       | 102/363 [00:06<00:14, 18.29it/s]
Loading 0:  29%|██▉       | 105/363 [00:06<00:18, 13.78it/s]
Loading 0:  29%|██▉       | 107/363 [00:06<00:19, 12.94it/s]
Loading 0:  30%|███       | 109/363 [00:07<00:20, 12.67it/s]
Loading 0:  31%|███       | 111/363 [00:07<00:18, 13.63it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:22, 11.08it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:14, 17.18it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:11, 20.77it/s]
Loading 0:  34%|███▍      | 125/363 [00:08<00:16, 14.85it/s]
Loading 0:  35%|███▌      | 128/363 [00:08<00:15, 15.64it/s]
Loading 0:  36%|███▌      | 130/363 [00:08<00:16, 14.00it/s]
Loading 0:  36%|███▋      | 132/363 [00:08<00:17, 13.18it/s]
Loading 0:  37%|███▋      | 136/363 [00:08<00:13, 17.26it/s]
Loading 0:  39%|███▊      | 140/363 [00:08<00:10, 20.77it/s]
Loading 0:  39%|███▉      | 143/363 [00:09<00:15, 14.32it/s]
Loading 0:  40%|███▉      | 145/363 [00:09<00:15, 13.77it/s]
Loading 0:  40%|████      | 147/363 [00:09<00:14, 14.70it/s]
Loading 0:  41%|████      | 149/363 [00:09<00:18, 11.88it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:11, 17.93it/s]
Loading 0:  44%|████▎     | 158/363 [00:10<00:09, 21.15it/s]
Loading 0:  44%|████▍     | 161/363 [00:10<00:13, 14.96it/s]
Loading 0:  45%|████▌     | 164/363 [00:10<00:12, 15.65it/s]
Loading 0:  46%|████▌     | 166/363 [00:10<00:14, 13.95it/s]
Loading 0:  46%|████▋     | 168/363 [00:10<00:14, 13.35it/s]
Loading 0:  47%|████▋     | 172/363 [00:11<00:10, 17.48it/s]
Loading 0:  48%|████▊     | 176/363 [00:11<00:08, 20.86it/s]
Loading 0:  49%|████▉     | 179/363 [00:11<00:12, 14.69it/s]
Loading 0:  50%|████▉     | 181/363 [00:11<00:13, 13.99it/s]
Loading 0:  50%|█████     | 183/363 [00:11<00:12, 14.86it/s]
Loading 0:  51%|█████     | 185/363 [00:12<00:15, 11.83it/s]
Loading 0:  52%|█████▏    | 190/363 [00:12<00:09, 17.71it/s]
Loading 0:  53%|█████▎    | 194/363 [00:12<00:08, 20.96it/s]
Loading 0:  54%|█████▍    | 197/363 [00:12<00:11, 14.71it/s]
Loading 0:  55%|█████▌    | 200/363 [00:12<00:10, 15.47it/s]
Loading 0:  55%|█████▌    | 200/363 [00:23<00:10, 15.47it/s]
Loading 0:  55%|█████▌    | 201/363 [00:27<04:50,  1.79s/it]
Loading 0:  56%|█████▌    | 203/363 [00:27<03:40,  1.38s/it]
Loading 0:  57%|█████▋    | 207/363 [00:28<02:06,  1.23it/s]
Loading 0:  58%|█████▊    | 210/363 [00:28<01:28,  1.74it/s]
Loading 0:  59%|█████▊    | 213/363 [00:28<01:04,  2.33it/s]
Loading 0:  59%|█████▉    | 215/363 [00:28<00:52,  2.83it/s]
Loading 0:  60%|█████▉    | 217/363 [00:28<00:42,  3.47it/s]
Loading 0:  60%|██████    | 219/363 [00:28<00:32,  4.41it/s]
Loading 0:  61%|██████    | 221/363 [00:29<00:28,  4.92it/s]
Loading 0:  62%|██████▏   | 226/363 [00:29<00:15,  8.60it/s]
Loading 0:  63%|██████▎   | 230/363 [00:29<00:11, 11.59it/s]
Loading 0:  64%|██████▍   | 233/363 [00:29<00:12, 10.22it/s]
Loading 0:  65%|██████▍   | 235/363 [00:30<00:12, 10.55it/s]
Loading 0:  65%|██████▌   | 237/363 [00:30<00:10, 11.55it/s]
Loading 0:  66%|██████▌   | 239/363 [00:30<00:12, 10.20it/s]
Loading 0:  67%|██████▋   | 244/363 [00:30<00:07, 15.22it/s]
Loading 0:  68%|██████▊   | 248/363 [00:30<00:06, 18.40it/s]
Loading 0:  69%|██████▉   | 251/363 [00:31<00:08, 13.58it/s]
Loading 0:  70%|██████▉   | 253/363 [00:31<00:08, 13.08it/s]
Loading 0:  70%|███████   | 255/363 [00:31<00:07, 14.05it/s]
Loading 0:  71%|███████   | 257/363 [00:31<00:09, 11.46it/s]
Loading 0:  72%|███████▏  | 262/363 [00:31<00:05, 17.00it/s]
Loading 0:  73%|███████▎  | 266/363 [00:31<00:04, 20.06it/s]
Loading 0:  74%|███████▍  | 269/363 [00:32<00:06, 14.18it/s]
Loading 0:  75%|███████▍  | 271/363 [00:32<00:06, 13.59it/s]
Loading 0:  75%|███████▌  | 273/363 [00:32<00:06, 14.51it/s]
Loading 0:  76%|███████▌  | 275/363 [00:32<00:07, 11.66it/s]
Loading 0:  77%|███████▋  | 280/363 [00:32<00:04, 17.32it/s]
Loading 0:  78%|███████▊  | 284/363 [00:33<00:03, 20.21it/s]
Loading 0:  79%|███████▉  | 287/363 [00:33<00:05, 14.09it/s]
Loading 0:  80%|███████▉  | 289/363 [00:33<00:05, 13.48it/s]
Loading 0:  80%|████████  | 291/363 [00:33<00:05, 14.37it/s]
Loading 0:  81%|████████  | 293/363 [00:34<00:06, 11.49it/s]
Loading 0:  82%|████████▏ | 298/363 [00:34<00:03, 16.87it/s]
Loading 0:  83%|████████▎ | 302/363 [00:34<00:03, 19.61it/s]
Loading 0:  84%|████████▍ | 305/363 [00:34<00:04, 13.84it/s]
Loading 0:  85%|████████▍ | 307/363 [00:34<00:04, 13.26it/s]
Loading 0:  85%|████████▌ | 309/363 [00:34<00:03, 14.19it/s]
Loading 0:  86%|████████▌ | 311/363 [00:35<00:04, 11.56it/s]
Loading 0:  87%|████████▋ | 316/363 [00:35<00:02, 17.07it/s]
Loading 0:  88%|████████▊ | 320/363 [00:35<00:02, 20.15it/s]
Loading 0:  89%|████████▉ | 323/363 [00:35<00:02, 14.13it/s]
Loading 0:  90%|████████▉ | 325/363 [00:36<00:02, 13.45it/s]
Loading 0:  90%|█████████ | 327/363 [00:36<00:02, 14.30it/s]
Loading 0:  91%|█████████ | 329/363 [00:36<00:02, 11.51it/s]
Loading 0:  92%|█████████▏| 334/363 [00:36<00:01, 17.17it/s]
Loading 0:  93%|█████████▎| 338/363 [00:36<00:01, 20.07it/s]
Loading 0:  94%|█████████▍| 341/363 [00:37<00:01, 14.25it/s]
Loading 0:  94%|█████████▍| 343/363 [00:37<00:01, 13.57it/s]
Loading 0:  95%|█████████▌| 345/363 [00:37<00:01, 14.52it/s]
Loading 0:  96%|█████████▌| 347/363 [00:37<00:01, 11.53it/s]
Loading 0:  97%|█████████▋| 352/363 [00:37<00:00, 17.18it/s]
Loading 0:  98%|█████████▊| 356/363 [00:37<00:00, 20.22it/s]
Loading 0:  99%|█████████▉| 359/363 [00:45<00:02,  1.47it/s]
Loading 0:  99%|█████████▉| 361/363 [00:45<00:01,  1.76it/s]
                                                            
Job rirv938-grpo-to-compare-75170-v1-mkmlizer completed after 259.5s with status: succeeded
Stopping job with name rirv938-grpo-to-compare-75170-v1-mkmlizer
Pipeline stage MKMLizer completed in 260.00s
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-75170-v1
Waiting for inference service rirv938-grpo-to-compare-75170-v1 to be ready
Failed to get response for submission chaiml-jesus-christ25042_7531_v3: HTTPConnectionPool(host='chaiml-jesus-christ25042-7531-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service rirv938-grpo-to-compare-75170-v1 ready after 130.44369959831238s
Pipeline stage MKMLDeployer completed in 130.98s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.179516315460205s
Received healthy response to inference request in 1.7677764892578125s
Received healthy response to inference request in 2.128176212310791s
Received healthy response to inference request in 1.5635957717895508s
Received healthy response to inference request in 2.2468810081481934s
5 requests
0 failed requests
5th percentile: 1.6044319152832032
10th percentile: 1.6452680587768556
20th percentile: 1.7269403457641601
30th percentile: 1.8398564338684082
40th percentile: 1.9840163230895995
50th percentile: 2.128176212310791
60th percentile: 2.1487122535705567
70th percentile: 2.1692482948303224
80th percentile: 2.1929892539978026
90th percentile: 2.2199351310729982
95th percentile: 2.233408069610596
99th percentile: 2.244186420440674
mean time: 1.9771891593933106
Pipeline stage StressChecker completed in 11.06s
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 0.70s
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_75170_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 3099.91s
Shutdown handler de-registered
rirv938-grpo-to-compare_75170_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-grpo-to-compare_75170_v1 status is now torndown due to DeploymentManager action