developer_uid: rirv938
submission_id: rirv938-mistral-12b-dpo-_9564_v2
model_name: rirv938-mistral-12b-dpo-_9564_v2
model_group: rirv938/mistral_12b_dpo_
status: torndown
timestamp: 2025-02-25T00:41:41+00:00
num_battles: 6033
num_wins: 2342
celo_rating: 1144.43
family_friendly_score: 0.6546000000000001
family_friendly_standard_error: 0.006724564521216225
submission_type: basic
model_repo: rirv938/mistral_12b_dpo_40k_2374_64_output_tokens_v2
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 768
max_output_tokens: 32
latencies: [{'batch_size': 1, 'throughput': 1.0983061233311155, 'latency_mean': 0.9104231536388397, 'latency_p50': 0.9087041616439819, 'latency_p90': 1.0716972827911377}, {'batch_size': 4, 'throughput': 2.0202068464808796, 'latency_mean': 1.9722905147075653, 'latency_p50': 1.9588110446929932, 'latency_p90': 2.3579087972640993}, {'batch_size': 5, 'throughput': 2.1369564194257626, 'latency_mean': 2.323362752199173, 'latency_p50': 2.331007719039917, 'latency_p90': 2.7422584772109984}, {'batch_size': 8, 'throughput': 2.373955885327496, 'latency_mean': 3.339717128276825, 'latency_p50': 3.2827842235565186, 'latency_p90': 4.072787880897522}, {'batch_size': 10, 'throughput': 2.433334879632449, 'latency_mean': 4.0744878447055815, 'latency_p50': 4.07287323474884, 'latency_p90': 4.915020775794983}, {'batch_size': 12, 'throughput': 2.4169140140859455, 'latency_mean': 4.90575434088707, 'latency_p50': 4.9497681856155396, 'latency_p90': 5.900539541244506}, {'batch_size': 15, 'throughput': 2.392259778802391, 'latency_mean': 6.170586402416229, 'latency_p50': 6.134899377822876, 'latency_p90': 7.124452662467957}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rirv938-mistral-12b-dpo-_9564_v2
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: rirv938/mistral_12b_dpo_40k_2374_64_output_tokens_v2
model_size: 13B
ranking_group: single
throughput_3p7s: 2.43
us_pacific_date: 2025-02-24
win_ratio: 0.38819824299685063
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': 32}
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-9564-v2-mkmlizer
Waiting for job on rirv938-mistral-12b-dpo-9564-v2-mkmlizer to finish
rirv938-mistral-12b-dpo-9564-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-mistral-12b-dpo-9564-v2-mkmlizer: ║     _____            __           __                                ║
rirv938-mistral-12b-dpo-9564-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-mistral-12b-dpo-9564-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-mistral-12b-dpo-9564-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-mistral-12b-dpo-9564-v2-mkmlizer: ║       /___/                                                         ║
rirv938-mistral-12b-dpo-9564-v2-mkmlizer: ║                                                                     ║
rirv938-mistral-12b-dpo-9564-v2-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-mistral-12b-dpo-9564-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-mistral-12b-dpo-9564-v2-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-mistral-12b-dpo-9564-v2-mkmlizer: ║                                                                     ║
rirv938-mistral-12b-dpo-9564-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-mistral-12b-dpo-9564-v2-mkmlizer: ║  belonging to:                                                      ║
rirv938-mistral-12b-dpo-9564-v2-mkmlizer: ║                                                                     ║
rirv938-mistral-12b-dpo-9564-v2-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-mistral-12b-dpo-9564-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-mistral-12b-dpo-9564-v2-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
rirv938-mistral-12b-dpo-9564-v2-mkmlizer: ║                                                                     ║
rirv938-mistral-12b-dpo-9564-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-mistral-12b-dpo-9564-v2-mkmlizer: Downloaded to shared memory in 67.724s
rirv938-mistral-12b-dpo-9564-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpjdxzpvml, device:0
rirv938-mistral-12b-dpo-9564-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-mistral-12b-dpo-9564-v2-mkmlizer: quantized model in 44.149s
rirv938-mistral-12b-dpo-9564-v2-mkmlizer: Processed model rirv938/mistral_12b_dpo_40k_2374_64_output_tokens_v2 in 111.873s
rirv938-mistral-12b-dpo-9564-v2-mkmlizer: creating bucket guanaco-mkml-models
rirv938-mistral-12b-dpo-9564-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-mistral-12b-dpo-9564-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-mistral-12b-dpo-9564-v2
rirv938-mistral-12b-dpo-9564-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-mistral-12b-dpo-9564-v2/config.json
rirv938-mistral-12b-dpo-9564-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-mistral-12b-dpo-9564-v2/special_tokens_map.json
rirv938-mistral-12b-dpo-9564-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-mistral-12b-dpo-9564-v2/tokenizer_config.json
rirv938-mistral-12b-dpo-9564-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-mistral-12b-dpo-9564-v2/flywheel_model.0.safetensors
rirv938-mistral-12b-dpo-9564-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:17, 20.94it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 27.92it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:14, 24.40it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:11, 30.81it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:15, 21.94it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:17, 18.84it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:13, 24.03it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:14, 23.26it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:13, 24.10it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:12, 25.29it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:13, 23.86it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:12, 24.93it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:14, 22.03it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:11, 27.17it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:10, 28.07it/s]
Loading 0:  17%|█▋        | 63/363 [00:02<00:15, 19.76it/s]
Loading 0:  18%|█▊        | 66/363 [00:02<00:14, 20.51it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:13, 22.15it/s]
Loading 0:  20%|█▉        | 72/363 [00:03<00:14, 20.48it/s]
Loading 0:  21%|██        | 77/363 [00:03<00:13, 21.29it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:10, 25.82it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:12, 22.66it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:10, 26.80it/s]
Loading 0:  26%|██▌       | 94/363 [00:03<00:09, 27.43it/s]
Loading 0:  27%|██▋       | 97/363 [00:04<00:10, 24.81it/s]
Loading 0:  28%|██▊       | 100/363 [00:04<00:10, 25.08it/s]
Loading 0:  28%|██▊       | 103/363 [00:04<00:14, 17.34it/s]
Loading 0:  29%|██▉       | 106/363 [00:04<00:14, 18.29it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:12, 20.04it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:11, 22.07it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:11, 22.21it/s]
Loading 0:  33%|███▎      | 120/363 [00:05<00:09, 26.05it/s]
Loading 0:  34%|███▍      | 123/363 [00:05<00:10, 23.74it/s]
Loading 0:  35%|███▍      | 127/363 [00:05<00:08, 27.33it/s]
Loading 0:  36%|███▌      | 130/363 [00:05<00:08, 27.93it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:08, 26.70it/s]
Loading 0:  38%|███▊      | 137/363 [00:05<00:08, 27.60it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:07, 30.59it/s]
Loading 0:  40%|███▉      | 145/363 [00:06<00:10, 20.36it/s]
Loading 0:  41%|████      | 149/363 [00:06<00:10, 19.95it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:08, 24.79it/s]
Loading 0:  44%|████▎     | 158/363 [00:06<00:09, 21.97it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:07, 25.99it/s]
Loading 0:  46%|████▌     | 167/363 [00:07<00:08, 22.27it/s]
Loading 0:  47%|████▋     | 172/363 [00:07<00:07, 26.10it/s]
Loading 0:  48%|████▊     | 176/363 [00:07<00:08, 22.89it/s]
Loading 0:  50%|████▉     | 181/363 [00:07<00:06, 26.79it/s]
Loading 0:  51%|█████     | 185/363 [00:08<00:10, 17.53it/s]
Loading 0:  52%|█████▏    | 190/363 [00:08<00:08, 21.29it/s]
Loading 0:  53%|█████▎    | 194/363 [00:08<00:08, 20.06it/s]
Loading 0:  55%|█████▍    | 199/363 [00:08<00:06, 23.98it/s]
Loading 0:  56%|█████▌    | 202/363 [00:08<00:06, 25.01it/s]
Loading 0:  56%|█████▋    | 205/363 [00:08<00:06, 24.20it/s]
Loading 0:  57%|█████▋    | 208/363 [00:08<00:06, 25.15it/s]
Loading 0:  58%|█████▊    | 212/363 [00:09<00:06, 22.04it/s]
Loading 0:  60%|█████▉    | 217/363 [00:09<00:05, 26.68it/s]
Loading 0:  61%|██████    | 222/363 [00:09<00:05, 27.83it/s]
Loading 0:  62%|██████▏   | 225/363 [00:09<00:07, 17.93it/s]
Loading 0:  63%|██████▎   | 230/363 [00:09<00:06, 19.09it/s]
Loading 0:  65%|██████▍   | 235/363 [00:10<00:05, 23.19it/s]
Loading 0:  66%|██████▌   | 238/363 [00:10<00:05, 24.41it/s]
Loading 0:  66%|██████▋   | 241/363 [00:10<00:05, 24.00it/s]
Loading 0:  67%|██████▋   | 244/363 [00:10<00:04, 24.67it/s]
Loading 0:  68%|██████▊   | 248/363 [00:10<00:05, 22.51it/s]
Loading 0:  70%|███████   | 255/363 [00:10<00:03, 29.55it/s]
Loading 0:  71%|███████▏  | 259/363 [00:10<00:03, 27.99it/s]
Loading 0:  72%|███████▏  | 263/363 [00:11<00:04, 22.62it/s]
Loading 0:  73%|███████▎  | 266/363 [00:11<00:04, 20.28it/s]
Loading 0:  75%|███████▌  | 273/363 [00:11<00:03, 27.59it/s]
Loading 0:  76%|███████▋  | 277/363 [00:11<00:03, 27.60it/s]
Loading 0:  78%|███████▊  | 282/363 [00:11<00:02, 30.19it/s]
Loading 0:  79%|███████▉  | 286/363 [00:11<00:02, 29.21it/s]
Loading 0:  80%|████████  | 291/363 [00:12<00:02, 31.83it/s]
Loading 0:  81%|████████▏ | 295/363 [00:12<00:02, 30.36it/s]
Loading 0:  82%|████████▏ | 299/363 [00:12<00:02, 29.57it/s]
Loading 0:  83%|████████▎ | 303/363 [00:12<00:01, 31.50it/s]
Loading 0:  85%|████████▍ | 307/363 [00:12<00:02, 21.41it/s]
Loading 0:  86%|████████▌ | 311/363 [00:13<00:02, 20.23it/s]
Loading 0:  87%|████████▋ | 316/363 [00:13<00:01, 24.78it/s]
Loading 0:  88%|████████▊ | 320/363 [00:13<00:01, 22.78it/s]
Loading 0:  90%|████████▉ | 325/363 [00:13<00:01, 27.64it/s]
Loading 0:  91%|█████████ | 329/363 [00:13<00:01, 24.53it/s]
Loading 0:  92%|█████████▏| 334/363 [00:13<00:00, 29.40it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:00, 25.70it/s]
Loading 0:  94%|█████████▍| 343/363 [00:14<00:00, 30.53it/s]
Loading 0:  96%|█████████▌| 347/363 [00:21<00:08,  1.97it/s]
Loading 0:  96%|█████████▋| 350/363 [00:21<00:05,  2.47it/s]
Loading 0:  97%|█████████▋| 353/363 [00:21<00:03,  3.15it/s]
Loading 0:  98%|█████████▊| 357/363 [00:21<00:01,  4.30it/s]
Loading 0: 100%|█████████▉| 362/363 [00:21<00:00,  6.40it/s]
                                                            

Job rirv938-mistral-12b-dpo-9564-v2-mkmlizer completed after 155.57s with status: succeeded
Stopping job with name rirv938-mistral-12b-dpo-9564-v2-mkmlizer
Pipeline stage MKMLizer completed in 156.04s
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-9564-v2
Waiting for inference service rirv938-mistral-12b-dpo-9564-v2 to be ready
Inference service rirv938-mistral-12b-dpo-9564-v2 ready after 240.7903869152069s
Pipeline stage MKMLDeployer completed in 241.32s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.3570349216461182s
Received healthy response to inference request in 1.0582013130187988s
Received healthy response to inference request in 0.83437180519104s
Received healthy response to inference request in 0.9794306755065918s
Received healthy response to inference request in 0.8027043342590332s
5 requests
0 failed requests
5th percentile: 0.8090378284454346
10th percentile: 0.815371322631836
20th percentile: 0.8280383110046386
30th percentile: 0.8633835792541504
40th percentile: 0.9214071273803711
50th percentile: 0.9794306755065918
60th percentile: 1.0109389305114747
70th percentile: 1.0424471855163575
80th percentile: 1.1179680347442627
90th percentile: 1.2375014781951905
95th percentile: 1.2972681999206543
99th percentile: 1.3450815773010254
mean time: 1.0063486099243164
Pipeline stage StressChecker completed in 6.39s
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 0.63s
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 0.82s
Shutdown handler de-registered
rirv938-mistral-12b-dpo-_9564_v2 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 2078.48s
Shutdown handler de-registered
rirv938-mistral-12b-dpo-_9564_v2 status is now inactive due to auto deactivation removed underperforming models
rirv938-mistral-12b-dpo-_9564_v2 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1