developer_uid: rirv938
submission_id: rirv938-mistral-24b-dpo_92099_v1
model_name: rirv938-mistral-24b-dpo_92099_v1
model_group: rirv938/mistral_24b_dpo_
status: torndown
timestamp: 2025-03-25T18:22:02+00:00
num_battles: 8286
num_wins: 4313
celo_rating: 1285.52
family_friendly_score: 0.5336000000000001
family_friendly_standard_error: 0.007055083840749166
submission_type: basic
model_repo: rirv938/mistral_24b_dpo_kl_10k_beta2_312_v3
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 768
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.3934622385054127, 'latency_mean': 2.5414517450332643, 'latency_p50': 2.529046416282654, 'latency_p90': 2.843105673789978}, {'batch_size': 3, 'throughput': 0.7934956784441505, 'latency_mean': 3.765666128396988, 'latency_p50': 3.7754056453704834, 'latency_p90': 4.134664130210877}, {'batch_size': 5, 'throughput': 1.0462016597185415, 'latency_mean': 4.745558667182922, 'latency_p50': 4.7486732006073, 'latency_p90': 5.31723940372467}, {'batch_size': 6, 'throughput': 1.133715080386399, 'latency_mean': 5.257258251905442, 'latency_p50': 5.2702367305755615, 'latency_p90': 5.871029782295227}, {'batch_size': 10, 'throughput': 1.3002590724127778, 'latency_mean': 7.633787140846253, 'latency_p50': 7.716609597206116, 'latency_p90': 8.584646415710449}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: rirv938-mistral-24b-dpo_92099_v1
is_internal_developer: True
language_model: rirv938/mistral_24b_dpo_kl_10k_beta2_312_v3
model_size: 24B
ranking_group: single
throughput_3p7s: 0.78
us_pacific_date: 2025-03-25
win_ratio: 0.5205165339126238
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-dpo-92099-v1-mkmlizer
Waiting for job on rirv938-mistral-24b-dpo-92099-v1-mkmlizer to finish
rirv938-mistral-24b-dpo-92099-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-mistral-24b-dpo-92099-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-mistral-24b-dpo-92099-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-mistral-24b-dpo-92099-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-mistral-24b-dpo-92099-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-mistral-24b-dpo-92099-v1-mkmlizer: ║       /___/                                                         ║
rirv938-mistral-24b-dpo-92099-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-92099-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-mistral-24b-dpo-92099-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-mistral-24b-dpo-92099-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-mistral-24b-dpo-92099-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-92099-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-mistral-24b-dpo-92099-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-mistral-24b-dpo-92099-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-92099-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-mistral-24b-dpo-92099-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-mistral-24b-dpo-92099-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
rirv938-mistral-24b-dpo-92099-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-92099-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-mistral-24b-dpo-92099-v1-mkmlizer: Downloaded to shared memory in 163.233s
rirv938-mistral-24b-dpo-92099-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp9m1iwnd1, device:0
rirv938-mistral-24b-dpo-92099-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-mistral-24b-dpo-92099-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-mistral-24b-dpo-92099-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-mistral-24b-dpo-92099-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-92099-v1
rirv938-mistral-24b-dpo-92099-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-92099-v1/config.json
rirv938-mistral-24b-dpo-92099-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-92099-v1/special_tokens_map.json
rirv938-mistral-24b-dpo-92099-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-92099-v1/tokenizer_config.json
rirv938-mistral-24b-dpo-92099-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-92099-v1/tokenizer.json
Failed to get response for submission nitral-ai-captain-eris_45741_v27: HTTPConnectionPool(host='nitral-ai-captain-eris-45741-v27-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
rirv938-mistral-24b-dpo-92099-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-92099-v1/flywheel_model.1.safetensors
rirv938-mistral-24b-dpo-92099-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-92099-v1/flywheel_model.0.safetensors
rirv938-mistral-24b-dpo-92099-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:12, 28.55it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:26, 13.33it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:17, 19.91it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:26, 13.36it/s]
Loading 0:   4%|▍         | 15/363 [00:01<00:31, 10.90it/s]
Loading 0:   5%|▌         | 19/363 [00:01<00:22, 15.31it/s]
Loading 0:   6%|▌         | 22/363 [00:01<00:23, 14.61it/s]
Loading 0:   7%|▋         | 24/363 [00:01<00:25, 13.47it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:19, 17.32it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:16, 20.56it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:23, 13.70it/s]
Loading 0:  10%|█         | 37/363 [00:02<00:25, 12.83it/s]
Loading 0:  11%|█         | 39/363 [00:02<00:23, 13.59it/s]
Loading 0:  11%|█▏        | 41/363 [00:02<00:29, 10.78it/s]
Loading 0:  13%|█▎        | 46/363 [00:03<00:19, 16.25it/s]
Loading 0:  14%|█▍        | 50/363 [00:03<00:16, 19.45it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:22, 13.65it/s]
Loading 0:  15%|█▌        | 55/363 [00:03<00:24, 12.63it/s]
Loading 0:  16%|█▌        | 57/363 [00:03<00:22, 13.35it/s]
Loading 0:  16%|█▋        | 59/363 [00:04<00:28, 10.58it/s]
Loading 0:  18%|█▊        | 64/363 [00:04<00:18, 16.05it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:15, 19.30it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:21, 13.49it/s]
Loading 0:  20%|██        | 73/363 [00:05<00:22, 12.72it/s]
Loading 0:  21%|██        | 75/363 [00:05<00:21, 13.43it/s]
Loading 0:  21%|██        | 77/363 [00:05<00:25, 11.07it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:16, 16.74it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:13, 20.09it/s]
Loading 0:  25%|██▍       | 89/363 [00:06<00:19, 14.11it/s]
Loading 0:  25%|██▌       | 91/363 [00:06<00:20, 13.37it/s]
Loading 0:  26%|██▌       | 95/363 [00:06<00:15, 17.27it/s]
Loading 0:  27%|██▋       | 99/363 [00:06<00:13, 19.79it/s]
Loading 0:  28%|██▊       | 102/363 [00:06<00:14, 17.66it/s]
Loading 0:  29%|██▉       | 105/363 [00:07<00:19, 13.25it/s]
Loading 0:  29%|██▉       | 107/363 [00:07<00:21, 11.92it/s]
Loading 0:  30%|███       | 109/363 [00:07<00:22, 11.21it/s]
Loading 0:  31%|███       | 111/363 [00:07<00:21, 11.98it/s]
Loading 0:  31%|███       | 113/363 [00:08<00:25,  9.91it/s]
Loading 0:  33%|███▎      | 118/363 [00:08<00:15, 15.41it/s]
Loading 0:  34%|███▎      | 122/363 [00:08<00:12, 18.59it/s]
Loading 0:  34%|███▍      | 125/363 [00:08<00:17, 13.28it/s]
Loading 0:  35%|███▍      | 127/363 [00:08<00:18, 12.79it/s]
Loading 0:  36%|███▌      | 129/363 [00:09<00:17, 13.60it/s]
Loading 0:  36%|███▌      | 131/363 [00:09<00:21, 10.89it/s]
Loading 0:  37%|███▋      | 136/363 [00:09<00:13, 16.46it/s]
Loading 0:  39%|███▊      | 140/363 [00:09<00:11, 19.46it/s]
Loading 0:  39%|███▉      | 143/363 [00:09<00:16, 13.27it/s]
Loading 0:  40%|███▉      | 145/363 [00:10<00:17, 12.37it/s]
Loading 0:  40%|████      | 147/363 [00:10<00:16, 13.05it/s]
Loading 0:  41%|████      | 149/363 [00:10<00:19, 10.82it/s]
Loading 0:  42%|████▏     | 154/363 [00:10<00:12, 16.41it/s]
Loading 0:  44%|████▎     | 158/363 [00:10<00:10, 19.21it/s]
Loading 0:  44%|████▍     | 161/363 [00:11<00:14, 14.27it/s]
Loading 0:  45%|████▍     | 163/363 [00:11<00:14, 13.43it/s]
Loading 0:  45%|████▌     | 165/363 [00:11<00:14, 14.12it/s]
Loading 0:  46%|████▌     | 167/363 [00:11<00:17, 11.25it/s]
Loading 0:  47%|████▋     | 172/363 [00:11<00:11, 16.65it/s]
Loading 0:  48%|████▊     | 176/363 [00:12<00:09, 19.68it/s]
Loading 0:  49%|████▉     | 179/363 [00:12<00:13, 13.47it/s]
Loading 0:  50%|████▉     | 181/363 [00:12<00:14, 12.76it/s]
Loading 0:  50%|█████     | 183/363 [00:12<00:13, 13.49it/s]
Loading 0:  51%|█████     | 185/363 [00:13<00:16, 10.80it/s]
Loading 0:  52%|█████▏    | 190/363 [00:13<00:10, 16.16it/s]
Loading 0:  53%|█████▎    | 194/363 [00:13<00:08, 19.31it/s]
Loading 0:  54%|█████▍    | 197/363 [00:13<00:12, 13.45it/s]
Loading 0:  55%|█████▍    | 199/363 [00:13<00:13, 12.35it/s]
Loading 0:  55%|█████▌    | 201/363 [00:29<04:49,  1.79s/it]
Loading 0:  56%|█████▌    | 202/363 [00:29<04:09,  1.55s/it]
Loading 0:  56%|█████▌    | 204/363 [00:29<03:01,  1.14s/it]
Loading 0:  57%|█████▋    | 207/363 [00:29<01:52,  1.39it/s]
Loading 0:  58%|█████▊    | 210/363 [00:29<01:14,  2.06it/s]
Loading 0:  58%|█████▊    | 212/363 [00:29<00:57,  2.63it/s]
Loading 0:  59%|█████▉    | 214/363 [00:30<00:47,  3.14it/s]
Loading 0:  60%|█████▉    | 216/363 [00:30<00:39,  3.71it/s]
Loading 0:  60%|██████    | 219/363 [00:30<00:26,  5.42it/s]
Loading 0:  61%|██████    | 221/363 [00:30<00:24,  5.76it/s]
Loading 0:  62%|██████▏   | 226/363 [00:30<00:13,  9.85it/s]
Loading 0:  63%|██████▎   | 230/363 [00:31<00:10, 13.18it/s]
Loading 0:  64%|██████▍   | 233/363 [00:31<00:11, 11.51it/s]
Loading 0:  65%|██████▌   | 236/363 [00:31<00:10, 12.66it/s]
Loading 0:  66%|██████▌   | 238/363 [00:31<00:10, 11.96it/s]
Loading 0:  66%|██████▌   | 240/363 [00:31<00:10, 11.98it/s]
Loading 0:  67%|██████▋   | 244/363 [00:32<00:07, 16.11it/s]
Loading 0:  68%|██████▊   | 248/363 [00:32<00:05, 20.10it/s]
Loading 0:  69%|██████▉   | 251/363 [00:32<00:07, 14.61it/s]
Loading 0:  70%|██████▉   | 254/363 [00:32<00:07, 15.28it/s]
Loading 0:  71%|███████   | 256/363 [00:32<00:07, 13.46it/s]
Loading 0:  71%|███████   | 258/363 [00:33<00:08, 12.93it/s]
Loading 0:  72%|███████▏  | 262/363 [00:33<00:05, 16.98it/s]
Loading 0:  73%|███████▎  | 266/363 [00:33<00:04, 20.01it/s]
Loading 0:  74%|███████▍  | 269/363 [00:33<00:06, 14.55it/s]
Loading 0:  75%|███████▍  | 271/363 [00:33<00:06, 13.95it/s]
Loading 0:  75%|███████▌  | 273/363 [00:34<00:06, 14.80it/s]
Loading 0:  76%|███████▌  | 275/363 [00:34<00:07, 12.13it/s]
Loading 0:  77%|███████▋  | 280/363 [00:34<00:04, 18.64it/s]
Loading 0:  78%|███████▊  | 284/363 [00:34<00:03, 22.19it/s]
Loading 0:  79%|███████▉  | 287/363 [00:34<00:05, 15.02it/s]
Loading 0:  80%|███████▉  | 290/363 [00:35<00:04, 15.82it/s]
Loading 0:  81%|████████  | 293/363 [00:35<00:05, 12.44it/s]
Loading 0:  82%|████████▏ | 298/363 [00:35<00:03, 17.37it/s]
Loading 0:  83%|████████▎ | 302/363 [00:35<00:02, 20.97it/s]
Loading 0:  84%|████████▍ | 305/363 [00:35<00:03, 15.65it/s]
Loading 0:  85%|████████▍ | 308/363 [00:36<00:03, 16.33it/s]
Loading 0:  86%|████████▌ | 311/363 [00:36<00:04, 12.68it/s]
Loading 0:  87%|████████▋ | 316/363 [00:36<00:02, 17.80it/s]
Loading 0:  88%|████████▊ | 320/363 [00:36<00:02, 21.27it/s]
Loading 0:  89%|████████▉ | 323/363 [00:37<00:02, 15.67it/s]
Loading 0:  90%|████████▉ | 326/363 [00:37<00:02, 16.30it/s]
Loading 0:  91%|█████████ | 329/363 [00:37<00:02, 13.05it/s]
Loading 0:  92%|█████████▏| 334/363 [00:37<00:01, 17.70it/s]
Loading 0:  93%|█████████▎| 338/363 [00:37<00:01, 20.88it/s]
Loading 0:  94%|█████████▍| 341/363 [00:38<00:01, 15.44it/s]
Loading 0:  95%|█████████▍| 344/363 [00:38<00:01, 16.26it/s]
Loading 0:  96%|█████████▌| 347/363 [00:38<00:01, 13.13it/s]
Loading 0:  97%|█████████▋| 352/363 [00:38<00:00, 18.37it/s]
Loading 0:  98%|█████████▊| 356/363 [00:38<00:00, 21.97it/s]
Loading 0:  99%|█████████▉| 360/363 [00:45<00:01,  1.74it/s]
Loading 0: 100%|██████████| 363/363 [00:46<00:00,  2.24it/s]
                                                            

Job rirv938-mistral-24b-dpo-92099-v1-mkmlizer completed after 298.26s with status: succeeded
Stopping job with name rirv938-mistral-24b-dpo-92099-v1-mkmlizer
Pipeline stage MKMLizer completed in 298.71s
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-mistral-24b-dpo-92099-v1
Waiting for inference service rirv938-mistral-24b-dpo-92099-v1 to be ready
Inference service rirv938-mistral-24b-dpo-92099-v1 ready after 100.3676586151123s
Pipeline stage MKMLDeployer completed in 100.81s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.1788296699523926s
Received healthy response to inference request in 2.7106592655181885s
Received healthy response to inference request in 2.6210758686065674s
Received healthy response to inference request in 2.6392674446105957s
Received healthy response to inference request in 2.939629077911377s
5 requests
0 failed requests
5th percentile: 2.624714183807373
10th percentile: 2.628352499008179
20th percentile: 2.63562912940979
30th percentile: 2.6535458087921144
40th percentile: 2.6821025371551515
50th percentile: 2.7106592655181885
60th percentile: 2.802247190475464
70th percentile: 2.893835115432739
80th percentile: 2.98746919631958
90th percentile: 3.0831494331359863
95th percentile: 3.1309895515441895
99th percentile: 3.169261646270752
mean time: 2.8178922653198244
Pipeline stage StressChecker completed in 15.53s
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 0.92s
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 0.64s
Shutdown handler de-registered
rirv938-mistral-24b-dpo_92099_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5457.30s
Shutdown handler de-registered
rirv938-mistral-24b-dpo_92099_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-mistral-24b-dpo_92099_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1