rirv938-dpo-to-compare-_98349

developer_uid: rirv938

submission_id: rirv938-dpo-to-compare-_98349_v1

model_name: rirv938-dpo-to-compare-_98349_v1

model_group: rirv938/dpo_to_compare_t

status: torndown

timestamp: 2025-04-27T03:45:57+00:00

num_battles: 8757

num_wins: 4582

celo_rating: 1307.01

family_friendly_score: 0.5152

family_friendly_standard_error: 0.007067799657602075

submission_type: basic

model_repo: rirv938/dpo_to_compare_to_grpo_10k_cp310_b2_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': 0.5271918252928958, 'latency_mean': 1.8967871820926667, 'latency_p50': 1.8996617794036865, 'latency_p90': 2.097113513946533}, {'batch_size': 3, 'throughput': 1.0817905394705254, 'latency_mean': 2.7600943851470947, 'latency_p50': 2.7690975666046143, 'latency_p90': 3.05865740776062}, {'batch_size': 5, 'throughput': 1.3925366755465434, 'latency_mean': 3.5741761100292204, 'latency_p50': 3.538199305534363, 'latency_p90': 4.078714323043823}, {'batch_size': 6, 'throughput': 1.5035238230206422, 'latency_mean': 3.9678998363018034, 'latency_p50': 3.9635424613952637, 'latency_p90': 4.515475249290466}, {'batch_size': 8, 'throughput': 1.6419278583827044, 'latency_mean': 4.839248636960983, 'latency_p50': 4.823786020278931, 'latency_p90': 5.418878102302552}, {'batch_size': 10, 'throughput': 1.7318281080467133, 'latency_mean': 5.7171405565738675, 'latency_p50': 5.698868751525879, 'latency_p90': 6.457947325706482}]

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

display_name: rirv938-dpo-to-compare-_98349_v1

is_internal_developer: True

language_model: rirv938/dpo_to_compare_to_grpo_10k_cp310_b2_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 1.44

us_pacific_date: 2025-04-26

win_ratio: 0.5232385520155304

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-dpo-to-compare-98349-v1-mkmlizer
Waiting for job on rirv938-dpo-to-compare-98349-v1-mkmlizer to finish
rirv938-dpo-to-compare-98349-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-dpo-to-compare-98349-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-dpo-to-compare-98349-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-dpo-to-compare-98349-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-dpo-to-compare-98349-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-dpo-to-compare-98349-v1-mkmlizer: ║       /___/                                                         ║
rirv938-dpo-to-compare-98349-v1-mkmlizer: ║                                                                     ║
rirv938-dpo-to-compare-98349-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-dpo-to-compare-98349-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-dpo-to-compare-98349-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-dpo-to-compare-98349-v1-mkmlizer: ║                                                                     ║
rirv938-dpo-to-compare-98349-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-dpo-to-compare-98349-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-dpo-to-compare-98349-v1-mkmlizer: ║                                                                     ║
rirv938-dpo-to-compare-98349-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-dpo-to-compare-98349-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-dpo-to-compare-98349-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-dpo-to-compare-98349-v1-mkmlizer: ║                                                                     ║
rirv938-dpo-to-compare-98349-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-dpo-to-compare-98349-v1-mkmlizer: Downloaded to shared memory in 161.832s
rirv938-dpo-to-compare-98349-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpevrnt4lt, device:0
rirv938-dpo-to-compare-98349-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-dpo-to-compare-98349-v1-mkmlizer: quantized model in 63.513s
rirv938-dpo-to-compare-98349-v1-mkmlizer: Processed model rirv938/dpo_to_compare_to_grpo_10k_cp310_b2_merged in 225.345s
rirv938-dpo-to-compare-98349-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-dpo-to-compare-98349-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-dpo-to-compare-98349-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-dpo-to-compare-98349-v1
rirv938-dpo-to-compare-98349-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-dpo-to-compare-98349-v1/special_tokens_map.json
rirv938-dpo-to-compare-98349-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-dpo-to-compare-98349-v1/tokenizer_config.json
rirv938-dpo-to-compare-98349-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-dpo-to-compare-98349-v1/tokenizer.json
rirv938-dpo-to-compare-98349-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-dpo-to-compare-98349-v1/flywheel_model.1.safetensors
rirv938-dpo-to-compare-98349-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-dpo-to-compare-98349-v1/flywheel_model.0.safetensors
rirv938-dpo-to-compare-98349-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:17, 20.94it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:20, 17.33it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:17, 20.57it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:25, 13.53it/s]
Loading 0:   4%|▍         | 15/363 [00:01<00:30, 11.31it/s]
Loading 0:   5%|▌         | 19/363 [00:01<00:21, 16.16it/s]
Loading 0:   6%|▌         | 22/363 [00:01<00:21, 15.78it/s]
Loading 0:   7%|▋         | 24/363 [00:01<00:22, 14.84it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:17, 19.60it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:14, 23.29it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:21, 15.45it/s]
Loading 0:  10%|█         | 38/363 [00:02<00:20, 15.69it/s]
Loading 0:  11%|█         | 40/363 [00:02<00:23, 13.97it/s]
Loading 0:  12%|█▏        | 42/363 [00:02<00:24, 13.20it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:18, 17.19it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:15, 20.45it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:21, 14.22it/s]
Loading 0:  15%|█▌        | 55/363 [00:03<00:23, 13.25it/s]
Loading 0:  16%|█▌        | 57/363 [00:03<00:21, 14.32it/s]
Loading 0:  16%|█▋        | 59/363 [00:03<00:25, 11.89it/s]
Loading 0:  18%|█▊        | 64/363 [00:04<00:16, 18.01it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:13, 21.47it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:18, 15.40it/s]
Loading 0:  20%|██        | 74/363 [00:04<00:18, 15.87it/s]
Loading 0:  21%|██        | 76/363 [00:04<00:20, 14.32it/s]
Loading 0:  21%|██▏       | 78/363 [00:05<00:21, 13.49it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:15, 17.72it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:12, 21.50it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:17, 15.40it/s]
Loading 0:  25%|██▌       | 92/363 [00:05<00:17, 15.71it/s]
Loading 0:  26%|██▌       | 95/363 [00:05<00:14, 18.06it/s]
Loading 0:  27%|██▋       | 99/363 [00:05<00:12, 21.60it/s]
Loading 0:  28%|██▊       | 102/363 [00:06<00:13, 19.83it/s]
Loading 0:  29%|██▉       | 105/363 [00:06<00:18, 14.25it/s]
Loading 0:  29%|██▉       | 107/363 [00:06<00:19, 13.33it/s]
Loading 0:  30%|███       | 109/363 [00:06<00:19, 13.14it/s]
Loading 0:  31%|███       | 111/363 [00:07<00:17, 14.05it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:22, 11.29it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:14, 17.19it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:11, 20.30it/s]
Loading 0:  34%|███▍      | 125/363 [00:07<00:16, 14.39it/s]
Loading 0:  35%|███▍      | 127/363 [00:08<00:17, 13.66it/s]
Loading 0:  36%|███▌      | 129/363 [00:08<00:15, 14.63it/s]
Loading 0:  36%|███▌      | 131/363 [00:08<00:20, 11.37it/s]
Loading 0:  37%|███▋      | 136/363 [00:08<00:13, 16.98it/s]
Loading 0:  39%|███▊      | 140/363 [00:08<00:11, 20.20it/s]
Loading 0:  39%|███▉      | 143/363 [00:09<00:15, 14.56it/s]
Loading 0:  40%|███▉      | 145/363 [00:09<00:15, 14.06it/s]
Loading 0:  41%|████      | 148/363 [00:09<00:14, 14.63it/s]
Loading 0:  41%|████▏     | 150/363 [00:09<00:15, 13.74it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:11, 17.56it/s]
Loading 0:  44%|████▎     | 158/363 [00:09<00:09, 20.74it/s]
Loading 0:  44%|████▍     | 161/363 [00:10<00:13, 14.83it/s]
Loading 0:  45%|████▍     | 163/363 [00:10<00:14, 13.80it/s]
Loading 0:  45%|████▌     | 165/363 [00:10<00:13, 14.66it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:16, 11.88it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:10, 17.55it/s]
Loading 0:  48%|████▊     | 176/363 [00:11<00:09, 20.75it/s]
Loading 0:  49%|████▉     | 179/363 [00:11<00:12, 14.72it/s]
Loading 0:  50%|████▉     | 181/363 [00:11<00:13, 13.99it/s]
Loading 0:  50%|█████     | 183/363 [00:11<00:12, 14.94it/s]
Loading 0:  51%|█████     | 185/363 [00:11<00:14, 12.02it/s]
Loading 0:  52%|█████▏    | 190/363 [00:12<00:09, 17.74it/s]
Loading 0:  53%|█████▎    | 194/363 [00:12<00:08, 20.98it/s]
Loading 0:  54%|█████▍    | 197/363 [00:12<00:11, 14.83it/s]
Loading 0:  55%|█████▍    | 199/363 [00:12<00:11, 13.88it/s]
Loading 0:  55%|█████▌    | 201/363 [00:27<04:33,  1.69s/it]
Loading 0:  56%|█████▌    | 203/363 [00:27<03:29,  1.31s/it]
Loading 0:  57%|█████▋    | 207/363 [00:27<02:01,  1.28it/s]
Loading 0:  58%|█████▊    | 210/363 [00:27<01:25,  1.80it/s]
Loading 0:  59%|█████▊    | 213/363 [00:27<01:02,  2.41it/s]
Loading 0:  59%|█████▉    | 215/363 [00:28<00:50,  2.92it/s]
Loading 0:  60%|█████▉    | 217/363 [00:28<00:40,  3.59it/s]
Loading 0:  60%|██████    | 219/363 [00:28<00:31,  4.54it/s]
Loading 0:  61%|██████    | 221/363 [00:28<00:27,  5.13it/s]
Loading 0:  62%|██████▏   | 226/363 [00:28<00:15,  9.03it/s]
Loading 0:  63%|██████▎   | 230/363 [00:28<00:10, 12.30it/s]
Loading 0:  64%|██████▍   | 233/363 [00:29<00:11, 11.02it/s]
Loading 0:  65%|██████▌   | 236/363 [00:29<00:10, 12.46it/s]
Loading 0:  66%|██████▌   | 239/363 [00:29<00:11, 11.05it/s]
Loading 0:  67%|██████▋   | 244/363 [00:29<00:07, 15.94it/s]
Loading 0:  68%|██████▊   | 248/363 [00:29<00:06, 19.08it/s]
Loading 0:  69%|██████▉   | 251/363 [00:30<00:07, 14.81it/s]
Loading 0:  70%|██████▉   | 254/363 [00:30<00:06, 15.80it/s]
Loading 0:  71%|███████   | 257/363 [00:30<00:08, 12.49it/s]
Loading 0:  72%|███████▏  | 262/363 [00:30<00:05, 17.54it/s]
Loading 0:  73%|███████▎  | 266/363 [00:31<00:04, 20.93it/s]
Loading 0:  74%|███████▍  | 269/363 [00:31<00:05, 15.71it/s]
Loading 0:  75%|███████▍  | 272/363 [00:31<00:05, 16.40it/s]
Loading 0:  76%|███████▌  | 275/363 [00:31<00:06, 13.09it/s]
Loading 0:  77%|███████▋  | 280/363 [00:31<00:04, 18.00it/s]
Loading 0:  78%|███████▊  | 284/363 [00:32<00:03, 21.18it/s]
Loading 0:  79%|███████▉  | 287/363 [00:32<00:04, 15.71it/s]
Loading 0:  80%|███████▉  | 290/363 [00:32<00:04, 16.37it/s]
Loading 0:  81%|████████  | 293/363 [00:32<00:05, 12.59it/s]
Loading 0:  82%|████████▏ | 298/363 [00:33<00:03, 17.61it/s]
Loading 0:  83%|████████▎ | 302/363 [00:33<00:02, 20.72it/s]
Loading 0:  84%|████████▍ | 305/363 [00:33<00:03, 15.58it/s]
Loading 0:  85%|████████▍ | 308/363 [00:33<00:03, 16.43it/s]
Loading 0:  86%|████████▌ | 311/363 [00:34<00:03, 13.12it/s]
Loading 0:  87%|████████▋ | 316/363 [00:34<00:02, 18.00it/s]
Loading 0:  88%|████████▊ | 320/363 [00:34<00:02, 21.23it/s]
Loading 0:  89%|████████▉ | 323/363 [00:34<00:02, 15.89it/s]
Loading 0:  90%|████████▉ | 326/363 [00:34<00:02, 16.41it/s]
Loading 0:  91%|█████████ | 329/363 [00:35<00:02, 13.14it/s]
Loading 0:  92%|█████████▏| 334/363 [00:35<00:01, 18.15it/s]
Loading 0:  93%|█████████▎| 338/363 [00:35<00:01, 21.16it/s]
Loading 0:  94%|█████████▍| 341/363 [00:35<00:01, 15.40it/s]
Loading 0:  95%|█████████▍| 344/363 [00:35<00:01, 16.10it/s]
Loading 0:  96%|█████████▌| 347/363 [00:36<00:01, 12.87it/s]
Loading 0:  97%|█████████▋| 352/363 [00:36<00:00, 17.85it/s]
Loading 0:  98%|█████████▊| 356/363 [00:36<00:00, 20.99it/s]
Loading 0:  99%|█████████▉| 359/363 [00:43<00:02,  1.60it/s]
Loading 0:  99%|█████████▉| 361/363 [00:43<00:01,  1.88it/s]
                                                            
Job rirv938-dpo-to-compare-98349-v1-mkmlizer completed after 258.41s with status: succeeded
Stopping job with name rirv938-dpo-to-compare-98349-v1-mkmlizer
Pipeline stage MKMLizer completed in 258.87s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-dpo-to-compare-98349-v1
Waiting for inference service rirv938-dpo-to-compare-98349-v1 to be ready
Inference service rirv938-dpo-to-compare-98349-v1 ready after 130.46231746673584s
Pipeline stage MKMLDeployer completed in 131.00s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5761830806732178s
Received healthy response to inference request in 2.0975234508514404s
Received healthy response to inference request in 2.0538830757141113s
Received healthy response to inference request in 2.2156620025634766s
Received healthy response to inference request in 1.9466791152954102s
5 requests
0 failed requests
5th percentile: 1.9681199073791504
10th percentile: 1.9895606994628907
20th percentile: 2.0324422836303713
30th percentile: 2.062611150741577
40th percentile: 2.0800673007965087
50th percentile: 2.0975234508514404
60th percentile: 2.144778871536255
70th percentile: 2.192034292221069
80th percentile: 2.287766218185425
90th percentile: 2.4319746494293213
95th percentile: 2.5040788650512695
99th percentile: 2.561762237548828
mean time: 2.1779861450195312
Pipeline stage StressChecker completed in 12.34s
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 0.68s
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 0.71s
Shutdown handler de-registered
rirv938-dpo-to-compare-_98349_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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-dpo-to-compare-98349-v1-profiler
Waiting for inference service rirv938-dpo-to-compare-98349-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4501.87s
Shutdown handler de-registered
rirv938-dpo-to-compare-_98349_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-dpo-to-compare-_98349_v1 status is now torndown due to DeploymentManager action