developer_uid: chai_backend_admin
submission_id: rirv938-mistral-12b-dpo_76739_v2
model_name: rirv938-mistral-12b-dpo_76739_v2
model_group: rirv938/mistral_12b_dpo_
status: torndown
timestamp: 2025-02-27T19:12:01+00:00
num_battles: 5924
num_wins: 3202
celo_rating: 1306.82
family_friendly_score: 0.604
family_friendly_standard_error: 0.00691641525647499
submission_type: basic
model_repo: rirv938/mistral_12b_dpo_40k_2374_96_output_tokens_much_ff_v2
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 768
max_output_tokens: 96
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.4575374609120651, 'latency_mean': 2.1855117547512055, 'latency_p50': 2.1895973682403564, 'latency_p90': 2.3412699460983277}, {'batch_size': 3, 'throughput': 0.9376084453826015, 'latency_mean': 3.1877552461624146, 'latency_p50': 3.1674681901931763, 'latency_p90': 3.4341307163238524}, {'batch_size': 5, 'throughput': 1.180972244475691, 'latency_mean': 4.205303918123246, 'latency_p50': 4.189687252044678, 'latency_p90': 4.555092620849609}, {'batch_size': 6, 'throughput': 1.262253267215537, 'latency_mean': 4.716227049827576, 'latency_p50': 4.720073938369751, 'latency_p90': 5.151536059379578}, {'batch_size': 8, 'throughput': 1.3318194770034715, 'latency_mean': 5.957415373325348, 'latency_p50': 5.934284448623657, 'latency_p90': 6.521563291549683}, {'batch_size': 10, 'throughput': 1.378971942662327, 'latency_mean': 7.192783131599426, 'latency_p50': 7.20848548412323, 'latency_p90': 7.853642416000366}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rirv938-mistral-12b-dpo_76739_v2
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: rirv938/mistral_12b_dpo_40k_2374_96_output_tokens_much_ff_v2
model_size: 13B
ranking_group: single
throughput_3p7s: 1.08
us_pacific_date: 2025-02-27
win_ratio: 0.5405131667792032
generation_params: {'temperature': 0.9, 'top_p': 0.9, 'min_p': 0.6, 'top_k': 80, 'presence_penalty': 0.5, 'frequency_penalty': 0.5, 'stopping_words': ['You:', '###', '\n', '</s>'], 'max_input_tokens': 768, 'best_of': 8, 'max_output_tokens': 96}
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-mistral-12b-dpo-76739-v2-mkmlizer
Waiting for job on rirv938-mistral-12b-dpo-76739-v2-mkmlizer to finish
rirv938-mistral-12b-dpo-76739-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-mistral-12b-dpo-76739-v2-mkmlizer: ║ _____ __ __ ║
rirv938-mistral-12b-dpo-76739-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rirv938-mistral-12b-dpo-76739-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rirv938-mistral-12b-dpo-76739-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rirv938-mistral-12b-dpo-76739-v2-mkmlizer: ║ /___/ ║
rirv938-mistral-12b-dpo-76739-v2-mkmlizer: ║ ║
rirv938-mistral-12b-dpo-76739-v2-mkmlizer: ║ Version: 0.12.8 ║
rirv938-mistral-12b-dpo-76739-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rirv938-mistral-12b-dpo-76739-v2-mkmlizer: ║ https://mk1.ai ║
rirv938-mistral-12b-dpo-76739-v2-mkmlizer: ║ ║
rirv938-mistral-12b-dpo-76739-v2-mkmlizer: ║ The license key for the current software has been verified as ║
rirv938-mistral-12b-dpo-76739-v2-mkmlizer: ║ belonging to: ║
rirv938-mistral-12b-dpo-76739-v2-mkmlizer: ║ ║
rirv938-mistral-12b-dpo-76739-v2-mkmlizer: ║ Chai Research Corp. ║
rirv938-mistral-12b-dpo-76739-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rirv938-mistral-12b-dpo-76739-v2-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
rirv938-mistral-12b-dpo-76739-v2-mkmlizer: ║ ║
rirv938-mistral-12b-dpo-76739-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-mistral-12b-dpo-76739-v2-mkmlizer: Downloaded to shared memory in 67.928s
rirv938-mistral-12b-dpo-76739-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpc2rfekft, device:0
rirv938-mistral-12b-dpo-76739-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-mistral-12b-dpo-76739-v2-mkmlizer: quantized model in 42.470s
rirv938-mistral-12b-dpo-76739-v2-mkmlizer: Processed model rirv938/mistral_12b_dpo_40k_2374_96_output_tokens_much_ff_v2 in 110.399s
rirv938-mistral-12b-dpo-76739-v2-mkmlizer: creating bucket guanaco-mkml-models
rirv938-mistral-12b-dpo-76739-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-mistral-12b-dpo-76739-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-mistral-12b-dpo-76739-v2
rirv938-mistral-12b-dpo-76739-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-mistral-12b-dpo-76739-v2/config.json
rirv938-mistral-12b-dpo-76739-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-mistral-12b-dpo-76739-v2/special_tokens_map.json
rirv938-mistral-12b-dpo-76739-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-mistral-12b-dpo-76739-v2/tokenizer_config.json
rirv938-mistral-12b-dpo-76739-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-mistral-12b-dpo-76739-v2/tokenizer.json
rirv938-mistral-12b-dpo-76739-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-mistral-12b-dpo-76739-v2/flywheel_model.0.safetensors
rirv938-mistral-12b-dpo-76739-v2-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:16, 21.47it/s] Loading 0: 3%|▎ | 10/363 [00:00<00:12, 27.26it/s] Loading 0: 4%|▍ | 14/363 [00:00<00:14, 24.02it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:11, 30.57it/s] Loading 0: 6%|▋ | 23/363 [00:00<00:15, 22.31it/s] Loading 0: 7%|▋ | 26/363 [00:01<00:16, 19.89it/s] Loading 0: 9%|▊ | 31/363 [00:01<00:13, 25.18it/s] Loading 0: 10%|▉ | 35/363 [00:01<00:12, 26.23it/s] Loading 0: 11%|█ | 39/363 [00:01<00:11, 27.33it/s] Loading 0: 12%|█▏ | 42/363 [00:01<00:12, 25.09it/s] Loading 0: 13%|█▎ | 46/363 [00:01<00:11, 28.25it/s] Loading 0: 14%|█▍ | 50/363 [00:02<00:12, 24.59it/s] Loading 0: 15%|█▌ | 56/363 [00:02<00:10, 29.35it/s] Loading 0: 17%|█▋ | 61/363 [00:02<00:12, 24.28it/s] Loading 0: 18%|█▊ | 64/363 [00:02<00:13, 21.38it/s] Loading 0: 20%|█▉ | 71/363 [00:02<00:10, 27.73it/s] Loading 0: 21%|██ | 75/363 [00:02<00:10, 26.50it/s] Loading 0: 21%|██▏ | 78/363 [00:03<00:11, 24.80it/s] Loading 0: 23%|██▎ | 82/363 [00:03<00:10, 27.83it/s] Loading 0: 24%|██▎ | 86/363 [00:03<00:11, 24.84it/s] Loading 0: 26%|██▌ | 93/363 [00:03<00:08, 31.08it/s] Loading 0: 27%|██▋ | 97/363 [00:03<00:08, 29.64it/s] Loading 0: 28%|██▊ | 101/363 [00:03<00:11, 23.54it/s] Loading 0: 29%|██▊ | 104/363 [00:04<00:12, 20.22it/s] Loading 0: 31%|███ | 111/363 [00:04<00:09, 26.75it/s] Loading 0: 31%|███▏ | 114/363 [00:04<00:09, 24.92it/s] Loading 0: 33%|███▎ | 118/363 [00:04<00:08, 27.54it/s] Loading 0: 34%|███▎ | 122/363 [00:04<00:09, 25.30it/s] Loading 0: 36%|███▌ | 129/363 [00:04<00:07, 30.99it/s] Loading 0: 37%|███▋ | 133/363 [00:05<00:07, 29.47it/s] Loading 0: 38%|███▊ | 137/363 [00:05<00:07, 29.55it/s] Loading 0: 39%|███▉ | 142/363 [00:05<00:08, 24.58it/s] Loading 0: 40%|███▉ | 145/363 [00:05<00:09, 23.27it/s] Loading 0: 41%|████ | 149/363 [00:05<00:09, 22.37it/s] Loading 0: 43%|████▎ | 156/363 [00:05<00:07, 28.94it/s] Loading 0: 44%|████▍ | 160/363 [00:06<00:07, 28.13it/s] Loading 0: 45%|████▌ | 165/363 [00:06<00:06, 29.86it/s] Loading 0: 47%|████▋ | 169/363 [00:06<00:06, 28.86it/s] Loading 0: 48%|████▊ | 174/363 [00:06<00:06, 31.05it/s] Loading 0: 49%|████▉ | 178/363 [00:06<00:06, 29.43it/s] Loading 0: 50%|█████ | 182/363 [00:06<00:07, 23.52it/s] Loading 0: 51%|█████ | 185/363 [00:07<00:08, 20.32it/s] Loading 0: 52%|█████▏ | 190/363 [00:07<00:06, 25.68it/s] Loading 0: 53%|█████▎ | 194/363 [00:07<00:07, 24.12it/s] Loading 0: 55%|█████▍ | 199/363 [00:07<00:05, 29.08it/s] Loading 0: 56%|█████▌ | 203/363 [00:07<00:06, 25.37it/s] Loading 0: 57%|█████▋ | 208/363 [00:07<00:05, 29.95it/s] Loading 0: 58%|█████▊ | 212/363 [00:08<00:05, 25.68it/s] Loading 0: 60%|██████ | 218/363 [00:08<00:04, 29.50it/s] Loading 0: 61%|██████▏ | 223/363 [00:08<00:05, 24.58it/s] Loading 0: 62%|██████▏ | 226/363 [00:08<00:06, 22.80it/s] Loading 0: 63%|██████▎ | 229/363 [00:08<00:05, 24.11it/s] Loading 0: 64%|██████▍ | 232/363 [00:08<00:05, 24.40it/s] Loading 0: 65%|██████▌ | 237/363 [00:09<00:04, 26.49it/s] Loading 0: 66%|██████▌ | 240/363 [00:09<00:05, 24.02it/s] Loading 0: 67%|██████▋ | 244/363 [00:09<00:04, 26.86it/s] Loading 0: 68%|██████▊ | 247/363 [00:09<00:04, 27.55it/s] Loading 0: 69%|██████▉ | 250/363 [00:09<00:04, 26.76it/s] Loading 0: 70%|██████▉ | 253/363 [00:09<00:04, 27.21it/s] Loading 0: 71%|███████ | 257/363 [00:09<00:04, 23.72it/s] Loading 0: 72%|███████▏ | 262/363 [00:10<00:03, 29.50it/s] Loading 0: 73%|███████▎ | 266/363 [00:10<00:05, 18.91it/s] Loading 0: 75%|███████▍ | 271/363 [00:10<00:03, 24.16it/s] Loading 0: 76%|███████▌ | 275/363 [00:10<00:03, 22.44it/s] Loading 0: 77%|███████▋ | 280/363 [00:10<00:03, 27.25it/s] Loading 0: 78%|███████▊ | 284/363 [00:11<00:03, 24.56it/s] Loading 0: 80%|███████▉ | 289/363 [00:11<00:02, 28.80it/s] Loading 0: 81%|████████ | 293/363 [00:11<00:02, 25.14it/s] Loading 0: 82%|████████▏ | 299/363 [00:11<00:02, 28.93it/s] Loading 0: 84%|████████▎ | 304/363 [00:11<00:02, 25.12it/s] Loading 0: 85%|████████▍ | 307/363 [00:11<00:02, 23.76it/s] Loading 0: 86%|████████▌ | 311/363 [00:12<00:02, 23.00it/s] Loading 0: 88%|████████▊ | 318/363 [00:12<00:01, 29.61it/s] Loading 0: 89%|████████▊ | 322/363 [00:12<00:01, 28.69it/s] Loading 0: 90%|█████████ | 327/363 [00:12<00:01, 30.72it/s] Loading 0: 91%|█████████ | 331/363 [00:12<00:01, 29.47it/s] Loading 0: 93%|█████████▎| 336/363 [00:12<00:00, 31.31it/s] Loading 0: 94%|█████████▎| 340/363 [00:12<00:00, 30.10it/s] Loading 0: 95%|█████████▍| 344/363 [00:19<00:09, 1.97it/s] Loading 0: 96%|█████████▌| 348/363 [00:20<00:05, 2.63it/s] Loading 0: 97%|█████████▋| 353/363 [00:20<00:02, 3.81it/s] Loading 0: 98%|█████████▊| 357/363 [00:20<00:01, 4.92it/s] Loading 0: 100%|█████████▉| 362/363 [00:20<00:00, 7.01it/s]
Job rirv938-mistral-12b-dpo-76739-v2-mkmlizer completed after 145.54s with status: succeeded
Stopping job with name rirv938-mistral-12b-dpo-76739-v2-mkmlizer
Pipeline stage MKMLizer completed in 146.05s
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-mistral-12b-dpo-76739-v2
Waiting for inference service rirv938-mistral-12b-dpo-76739-v2 to be ready
Inference service rirv938-mistral-12b-dpo-76739-v2 ready after 291.303320646286s
Pipeline stage MKMLDeployer completed in 292.02s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8388807773590088s
Received healthy response to inference request in 1.7773256301879883s
Received healthy response to inference request in 1.2556343078613281s
Received healthy response to inference request in 1.3307578563690186s
Received healthy response to inference request in 1.1102173328399658s
5 requests
0 failed requests
5th percentile: 1.1393007278442382
10th percentile: 1.1683841228485108
20th percentile: 1.2265509128570558
30th percentile: 1.2706590175628663
40th percentile: 1.3007084369659423
50th percentile: 1.3307578563690186
60th percentile: 1.5093849658966063
70th percentile: 1.6880120754241943
80th percentile: 1.7896366596221924
90th percentile: 1.8142587184906005
95th percentile: 1.8265697479248046
99th percentile: 1.836418571472168
mean time: 1.4625631809234618
Pipeline stage StressChecker completed in 8.71s
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 0.69s
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 0.66s
Shutdown handler de-registered
rirv938-mistral-12b-dpo_76739_v2 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 0.11s
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-mistral-12b-dpo-76739-v2-profiler
Waiting for inference service rirv938-mistral-12b-dpo-76739-v2-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 2843.29s
Shutdown handler de-registered
rirv938-mistral-12b-dpo_76739_v2 status is now inactive due to auto deactivation removed underperforming models
rirv938-mistral-12b-dpo_76739_v2 status is now torndown due to DeploymentManager action