developer_uid: rirv938
submission_id: rirv938-mistral-24b-rou_91022_v2
model_name: rirv938-mistral-24b-rou_91022_v2
model_group: rirv938/mistral_24b_roun
status: torndown
timestamp: 2025-03-07T06:17:11+00:00
num_battles: 12143
num_wins: 6495
celo_rating: 1310.25
family_friendly_score: 0.5424
family_friendly_standard_error: 0.0070455977744972075
submission_type: basic
model_repo: rirv938/mistral_24b_round_2_dpo_40k_85w_pref_20w_swear_2500_v2
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 768
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.38730765965650416, 'latency_mean': 2.581863524913788, 'latency_p50': 2.5894707441329956, 'latency_p90': 2.8684033393859862}, {'batch_size': 3, 'throughput': 0.7910497089208887, 'latency_mean': 3.7814655077457426, 'latency_p50': 3.776077628135681, 'latency_p90': 4.155105233192444}, {'batch_size': 5, 'throughput': 1.0523277576060073, 'latency_mean': 4.7300887775421145, 'latency_p50': 4.68654203414917, 'latency_p90': 5.328313899040222}, {'batch_size': 6, 'throughput': 1.1377180478888893, 'latency_mean': 5.250381946563721, 'latency_p50': 5.286876201629639, 'latency_p90': 5.838148760795593}, {'batch_size': 10, 'throughput': 1.2955833815307776, 'latency_mean': 7.627057571411132, 'latency_p50': 7.5449806451797485, 'latency_p90': 8.705344033241271}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: rirv938-mistral-24b-rou_91022_v2
is_internal_developer: True
language_model: rirv938/mistral_24b_round_2_dpo_40k_85w_pref_20w_swear_2500_v2
model_size: 24B
ranking_group: single
throughput_3p7s: 0.77
us_pacific_date: 2025-03-06
win_ratio: 0.5348760602816437
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': ['\n', '</s>', '###', 'You:'], 'max_input_tokens': 768, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '[INST]', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '[/INST]{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-24b-rou-91022-v2-mkmlizer
Waiting for job on rirv938-mistral-24b-rou-91022-v2-mkmlizer to finish
rirv938-mistral-24b-rou-91022-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-mistral-24b-rou-91022-v2-mkmlizer: ║ _____ __ __ ║
rirv938-mistral-24b-rou-91022-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rirv938-mistral-24b-rou-91022-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rirv938-mistral-24b-rou-91022-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rirv938-mistral-24b-rou-91022-v2-mkmlizer: ║ /___/ ║
rirv938-mistral-24b-rou-91022-v2-mkmlizer: ║ ║
rirv938-mistral-24b-rou-91022-v2-mkmlizer: ║ Version: 0.12.8 ║
rirv938-mistral-24b-rou-91022-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rirv938-mistral-24b-rou-91022-v2-mkmlizer: ║ https://mk1.ai ║
rirv938-mistral-24b-rou-91022-v2-mkmlizer: ║ ║
rirv938-mistral-24b-rou-91022-v2-mkmlizer: ║ The license key for the current software has been verified as ║
rirv938-mistral-24b-rou-91022-v2-mkmlizer: ║ belonging to: ║
rirv938-mistral-24b-rou-91022-v2-mkmlizer: ║ ║
rirv938-mistral-24b-rou-91022-v2-mkmlizer: ║ Chai Research Corp. ║
rirv938-mistral-24b-rou-91022-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rirv938-mistral-24b-rou-91022-v2-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
rirv938-mistral-24b-rou-91022-v2-mkmlizer: ║ ║
rirv938-mistral-24b-rou-91022-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-mistral-24b-rou-91022-v2-mkmlizer: Downloaded to shared memory in 131.534s
rirv938-mistral-24b-rou-91022-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp1_us7473, device:0
rirv938-mistral-24b-rou-91022-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-mistral-24b-rou-91022-v2-mkmlizer: quantized model in 62.447s
rirv938-mistral-24b-rou-91022-v2-mkmlizer: Processed model rirv938/mistral_24b_round_2_dpo_40k_85w_pref_20w_swear_2500_v2 in 193.982s
rirv938-mistral-24b-rou-91022-v2-mkmlizer: creating bucket guanaco-mkml-models
rirv938-mistral-24b-rou-91022-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-mistral-24b-rou-91022-v2/config.json
rirv938-mistral-24b-rou-91022-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-mistral-24b-rou-91022-v2/special_tokens_map.json
rirv938-mistral-24b-rou-91022-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-mistral-24b-rou-91022-v2/tokenizer_config.json
rirv938-mistral-24b-rou-91022-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-mistral-24b-rou-91022-v2/tokenizer.json
rirv938-mistral-24b-rou-91022-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-rou-91022-v2/flywheel_model.1.safetensors
rirv938-mistral-24b-rou-91022-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-rou-91022-v2/flywheel_model.0.safetensors
rirv938-mistral-24b-rou-91022-v2-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 4/363 [00:00<00:17, 20.61it/s] Loading 0: 2%|▏ | 7/363 [00:00<00:20, 17.63it/s] Loading 0: 3%|▎ | 11/363 [00:00<00:15, 22.44it/s] Loading 0: 4%|▍ | 14/363 [00:00<00:24, 13.98it/s] Loading 0: 4%|▍ | 16/363 [00:01<00:25, 13.45it/s] Loading 0: 5%|▌ | 19/363 [00:01<00:20, 16.43it/s] Loading 0: 6%|▌ | 21/363 [00:01<00:20, 16.68it/s] Loading 0: 6%|▋ | 23/363 [00:01<00:26, 12.74it/s] Loading 0: 8%|▊ | 29/363 [00:01<00:15, 21.57it/s] Loading 0: 9%|▉ | 33/363 [00:01<00:16, 19.69it/s] Loading 0: 10%|▉ | 36/363 [00:02<00:22, 14.56it/s] Loading 0: 11%|█ | 39/363 [00:02<00:19, 16.78it/s] Loading 0: 12%|█▏ | 42/363 [00:02<00:21, 14.69it/s] Loading 0: 13%|█▎ | 46/363 [00:02<00:17, 18.36it/s] Loading 0: 14%|█▍ | 50/363 [00:02<00:14, 22.02it/s] Loading 0: 15%|█▍ | 53/363 [00:03<00:20, 15.36it/s] Loading 0: 15%|█▌ | 56/363 [00:03<00:19, 15.91it/s] Loading 0: 16%|█▋ | 59/363 [00:03<00:24, 12.60it/s] Loading 0: 18%|█▊ | 64/363 [00:03<00:17, 17.42it/s] Loading 0: 19%|█▊ | 68/363 [00:03<00:13, 21.17it/s] Loading 0: 20%|█▉ | 71/363 [00:04<00:18, 15.49it/s] Loading 0: 20%|██ | 74/363 [00:04<00:17, 16.18it/s] Loading 0: 21%|██ | 77/363 [00:04<00:22, 12.78it/s] Loading 0: 23%|██▎ | 82/363 [00:04<00:16, 17.50it/s] Loading 0: 24%|██▎ | 86/363 [00:05<00:13, 20.66it/s] Loading 0: 25%|██▍ | 89/363 [00:05<00:17, 15.27it/s] Loading 0: 25%|██▌ | 92/363 [00:05<00:17, 15.81it/s] Loading 0: 27%|██▋ | 97/363 [00:05<00:12, 20.99it/s] Loading 0: 28%|██▊ | 101/363 [00:05<00:11, 22.09it/s] Loading 0: 29%|██▊ | 104/363 [00:06<00:13, 18.58it/s] Loading 0: 29%|██▉ | 107/363 [00:06<00:17, 14.25it/s] Loading 0: 30%|███ | 109/363 [00:06<00:18, 13.64it/s] Loading 0: 31%|███ | 111/363 [00:06<00:17, 14.36it/s] Loading 0: 31%|███ | 113/363 [00:06<00:20, 12.20it/s] Loading 0: 33%|███▎ | 119/363 [00:07<00:12, 20.25it/s] Loading 0: 34%|███▍ | 123/363 [00:07<00:12, 19.15it/s] Loading 0: 35%|███▍ | 126/363 [00:07<00:16, 14.08it/s] Loading 0: 36%|███▌ | 129/363 [00:07<00:14, 16.28it/s] Loading 0: 36%|███▋ | 132/363 [00:08<00:15, 14.91it/s] Loading 0: 38%|███▊ | 137/363 [00:08<00:11, 20.36it/s] Loading 0: 39%|███▉ | 141/363 [00:08<00:11, 19.31it/s] Loading 0: 40%|███▉ | 144/363 [00:08<00:14, 14.64it/s] Loading 0: 40%|████ | 147/363 [00:08<00:12, 16.78it/s] Loading 0: 41%|████▏ | 150/363 [00:09<00:14, 14.93it/s] Loading 0: 42%|████▏ | 154/363 [00:09<00:11, 18.78it/s] Loading 0: 44%|████▎ | 158/363 [00:09<00:09, 22.24it/s] Loading 0: 44%|████▍ | 161/363 [00:09<00:12, 15.90it/s] Loading 0: 45%|████▌ | 164/363 [00:09<00:12, 16.56it/s] Loading 0: 46%|████▌ | 167/363 [00:10<00:15, 12.97it/s] Loading 0: 47%|████▋ | 172/363 [00:10<00:10, 18.41it/s] Loading 0: 48%|████▊ | 176/363 [00:10<00:08, 21.88it/s] Loading 0: 50%|████▉ | 180/363 [00:10<00:13, 13.87it/s] Loading 0: 50%|█████ | 183/363 [00:11<00:11, 15.91it/s] Loading 0: 51%|█████ | 186/363 [00:11<00:12, 14.70it/s] Loading 0: 53%|█████▎ | 191/363 [00:11<00:08, 19.86it/s] Loading 0: 54%|█████▎ | 195/363 [00:11<00:08, 18.93it/s] Loading 0: 55%|█████▍ | 198/363 [00:11<00:11, 14.58it/s] Loading 0: 55%|█████▌ | 201/363 [00:26<03:33, 1.32s/it] Loading 0: 56%|█████▌ | 203/363 [00:26<02:53, 1.09s/it] Loading 0: 57%|█████▋ | 207/363 [00:26<01:49, 1.42it/s] Loading 0: 58%|█████▊ | 210/363 [00:27<01:19, 1.93it/s] Loading 0: 59%|█████▊ | 213/363 [00:27<00:59, 2.53it/s] Loading 0: 59%|█████▉ | 215/363 [00:27<00:48, 3.02it/s] Loading 0: 60%|█████▉ | 217/363 [00:27<00:39, 3.67it/s] Loading 0: 60%|██████ | 219/363 [00:27<00:31, 4.58it/s] Loading 0: 61%|██████ | 221/363 [00:28<00:27, 5.15it/s] Loading 0: 62%|██████▏ | 226/363 [00:28<00:15, 9.12it/s] Loading 0: 64%|██████▎ | 231/363 [00:28<00:11, 11.78it/s] Loading 0: 64%|██████▍ | 234/363 [00:28<00:12, 10.69it/s] Loading 0: 65%|██████▌ | 237/363 [00:28<00:09, 12.84it/s] Loading 0: 66%|██████▌ | 240/363 [00:29<00:09, 12.57it/s] Loading 0: 67%|██████▋ | 244/363 [00:29<00:07, 16.47it/s] Loading 0: 69%|██████▊ | 249/363 [00:29<00:06, 17.81it/s] Loading 0: 69%|██████▉ | 252/363 [00:29<00:07, 14.06it/s] Loading 0: 70%|███████ | 255/363 [00:29<00:06, 16.17it/s] Loading 0: 71%|███████ | 258/363 [00:30<00:07, 14.34it/s] Loading 0: 72%|███████▏ | 262/363 [00:30<00:05, 18.13it/s] Loading 0: 73%|███████▎ | 266/363 [00:30<00:04, 21.83it/s] Loading 0: 74%|███████▍ | 269/363 [00:30<00:05, 15.77it/s] Loading 0: 75%|███████▍ | 272/363 [00:30<00:05, 16.44it/s] Loading 0: 76%|███████▌ | 275/363 [00:31<00:06, 13.13it/s] Loading 0: 77%|███████▋ | 280/363 [00:31<00:04, 18.04it/s] Loading 0: 78%|███████▊ | 284/363 [00:31<00:03, 21.52it/s] Loading 0: 79%|███████▉ | 287/363 [00:31<00:04, 15.70it/s] Loading 0: 80%|███████▉ | 290/363 [00:32<00:04, 16.58it/s] Loading 0: 81%|████████ | 293/363 [00:32<00:05, 13.28it/s] Loading 0: 82%|████████▏ | 299/363 [00:32<00:03, 19.99it/s] Loading 0: 83%|████████▎ | 303/363 [00:32<00:03, 19.50it/s] Loading 0: 84%|████████▍ | 306/363 [00:33<00:03, 14.80it/s] Loading 0: 85%|████████▌ | 309/363 [00:33<00:03, 16.87it/s] Loading 0: 86%|████████▌ | 312/363 [00:33<00:03, 15.04it/s] Loading 0: 87%|████████▋ | 317/363 [00:33<00:02, 20.28it/s] Loading 0: 88%|████████▊ | 321/363 [00:33<00:02, 18.99it/s] Loading 0: 89%|████████▉ | 324/363 [00:34<00:02, 14.53it/s] Loading 0: 90%|█████████ | 327/363 [00:34<00:02, 16.59it/s] Loading 0: 91%|█████████ | 330/363 [00:34<00:02, 14.61it/s] Loading 0: 92%|█████████▏| 334/363 [00:34<00:01, 18.01it/s] Loading 0: 93%|█████████▎| 338/363 [00:34<00:01, 21.06it/s] Loading 0: 94%|█████████▍| 341/363 [00:35<00:01, 14.88it/s] Loading 0: 95%|█████████▍| 344/363 [00:35<00:01, 15.73it/s] Loading 0: 95%|█████████▌| 346/363 [00:35<00:01, 13.94it/s] Loading 0: 96%|█████████▌| 348/363 [00:35<00:01, 13.68it/s] Loading 0: 97%|█████████▋| 353/363 [00:35<00:00, 19.90it/s] Loading 0: 98%|█████████▊| 357/363 [00:42<00:03, 1.59it/s] Loading 0: 99%|█████████▉| 360/363 [00:42<00:01, 2.09it/s] Loading 0: 100%|█████████▉| 362/363 [00:43<00:00, 2.51it/s]
Job rirv938-mistral-24b-rou-91022-v2-mkmlizer completed after 226.32s with status: succeeded
Stopping job with name rirv938-mistral-24b-rou-91022-v2-mkmlizer
Pipeline stage MKMLizer completed in 226.82s
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-24b-rou-91022-v2
Waiting for inference service rirv938-mistral-24b-rou-91022-v2 to be ready
Inference service rirv938-mistral-24b-rou-91022-v2 ready after 100.36610221862793s
Pipeline stage MKMLDeployer completed in 100.89s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.927675485610962s
Received healthy response to inference request in 2.4961507320404053s
Received healthy response to inference request in 2.7479143142700195s
Received healthy response to inference request in 2.4654617309570312s
Received healthy response to inference request in 2.4023022651672363s
5 requests
0 failed requests
5th percentile: 2.4149341583251953
10th percentile: 2.4275660514831543
20th percentile: 2.4528298377990723
30th percentile: 2.4715995311737062
40th percentile: 2.4838751316070558
50th percentile: 2.4961507320404053
60th percentile: 2.596856164932251
70th percentile: 2.6975615978240968
80th percentile: 2.783866548538208
90th percentile: 2.855771017074585
95th percentile: 2.8917232513427735
99th percentile: 2.9204850387573242
mean time: 2.6079009056091307
Pipeline stage StressChecker completed in 14.28s
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 0.62s
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 0.70s
Shutdown handler de-registered
rirv938-mistral-24b-rou_91022_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 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-mistral-24b-rou-91022-v2-profiler
Waiting for inference service rirv938-mistral-24b-rou-91022-v2-profiler to be ready
Inference service rirv938-mistral-24b-rou-91022-v2-profiler ready after 100.45986032485962s
Pipeline stage MKMLProfilerDeployer completed in 100.97s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-mistral-24b-523aa21739ccf12fae1ce759c279e6d0-deplob9ntl:/code/chaiverse_profiler_1741328760 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-mistral-24b-523aa21739ccf12fae1ce759c279e6d0-deplob9ntl --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1741328760 && python profiles.py profile --best_of_n 8 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 768 --output_tokens 64 --summary /code/chaiverse_profiler_1741328760/summary.json'
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 2748.26s
Shutdown handler de-registered
rirv938-mistral-24b-rou_91022_v2 status is now inactive due to auto deactivation removed underperforming models
rirv938-mistral-24b-rou_91022_v2 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1