rica40325-10-14dpo

developer_uid: azuruce

submission_id: rica40325-10-14dpo_v12

model_name: rica40325-10-14dpo_v12

model_group: rica40325/10_14dpo

status: torndown

timestamp: 2025-01-13T23:16:21+00:00

num_battles: 8385

num_wins: 4280

celo_rating: 1275.08

family_friendly_score: 0.5913999999999999

family_friendly_standard_error: 0.006951921173316049

submission_type: basic

model_repo: rica40325/10_14dpo

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.6366871371741213, 'latency_mean': 1.5705688071250916, 'latency_p50': 1.5606343746185303, 'latency_p90': 1.7343163967132569}, {'batch_size': 3, 'throughput': 1.2619641263984567, 'latency_mean': 2.3617577719688416, 'latency_p50': 2.358994722366333, 'latency_p90': 2.630557322502136}, {'batch_size': 5, 'throughput': 1.6017460898427167, 'latency_mean': 3.105601280927658, 'latency_p50': 3.109052896499634, 'latency_p90': 3.453807187080383}, {'batch_size': 6, 'throughput': 1.712625356906856, 'latency_mean': 3.4831046414375306, 'latency_p50': 3.48068904876709, 'latency_p90': 3.917474126815796}, {'batch_size': 8, 'throughput': 1.8736370783539131, 'latency_mean': 4.24577365398407, 'latency_p50': 4.193697452545166, 'latency_p90': 4.770810627937317}, {'batch_size': 10, 'throughput': 1.9453549918950925, 'latency_mean': 5.093292201757431, 'latency_p50': 5.11105477809906, 'latency_p90': 5.755079245567321}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rica40325-10-14dpo_v12

is_internal_developer: False

language_model: rica40325/10_14dpo

model_size: 13B

ranking_group: single

throughput_3p7s: 1.78

us_pacific_date: 2025-01-13

win_ratio: 0.5104353011329755

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.001, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['<|im_end|>', 'Bot:', '\n', '</s>', '<|eot_id|>', 'User:', 'You:', 'Me:', '####'], 'max_input_tokens': 1024, 'best_of': 4, '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 rica40325-10-14dpo-v12-mkmlizer
Waiting for job on rica40325-10-14dpo-v12-mkmlizer to finish
rica40325-10-14dpo-v12-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-10-14dpo-v12-mkmlizer: ║     _____            __           __                                ║
rica40325-10-14dpo-v12-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rica40325-10-14dpo-v12-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rica40325-10-14dpo-v12-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rica40325-10-14dpo-v12-mkmlizer: ║       /___/                                                         ║
rica40325-10-14dpo-v12-mkmlizer: ║                                                                     ║
rica40325-10-14dpo-v12-mkmlizer: ║  Version: 0.11.12                                                   ║
rica40325-10-14dpo-v12-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rica40325-10-14dpo-v12-mkmlizer: ║  https://mk1.ai                                                     ║
rica40325-10-14dpo-v12-mkmlizer: ║                                                                     ║
rica40325-10-14dpo-v12-mkmlizer: ║  The license key for the current software has been verified as      ║
rica40325-10-14dpo-v12-mkmlizer: ║  belonging to:                                                      ║
rica40325-10-14dpo-v12-mkmlizer: ║                                                                     ║
rica40325-10-14dpo-v12-mkmlizer: ║  Chai Research Corp.                                                ║
rica40325-10-14dpo-v12-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rica40325-10-14dpo-v12-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
rica40325-10-14dpo-v12-mkmlizer: ║                                                                     ║
rica40325-10-14dpo-v12-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rica40325-10-14dpo-v12-mkmlizer: Downloaded to shared memory in 57.677s
rica40325-10-14dpo-v12-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp46faf6uo, device:0
rica40325-10-14dpo-v12-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rica40325-10-14dpo-v12-mkmlizer: quantized model in 42.522s
rica40325-10-14dpo-v12-mkmlizer: Processed model rica40325/10_14dpo in 100.199s
rica40325-10-14dpo-v12-mkmlizer: creating bucket guanaco-mkml-models
rica40325-10-14dpo-v12-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-10-14dpo-v12-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-10-14dpo-v12
rica40325-10-14dpo-v12-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-10-14dpo-v12/config.json
rica40325-10-14dpo-v12-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-10-14dpo-v12/special_tokens_map.json
rica40325-10-14dpo-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-10-14dpo-v12/tokenizer_config.json
rica40325-10-14dpo-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-10-14dpo-v12/tokenizer.json
rica40325-10-14dpo-v12-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-10-14dpo-v12/flywheel_model.0.safetensors
rica40325-10-14dpo-v12-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 22.04it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 27.60it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:14, 24.17it/s]
Loading 0:   6%|▌         | 20/363 [00:00<00:10, 33.34it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:14, 24.01it/s]
Loading 0:   7%|▋         | 27/363 [00:01<00:14, 22.45it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:13, 25.52it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:13, 25.20it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:11, 28.31it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:11, 27.48it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 29.82it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 28.14it/s]
Loading 0:  15%|█▌        | 56/363 [00:02<00:11, 27.61it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:10, 30.29it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:14, 20.08it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:11, 26.48it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:11, 26.17it/s]
Loading 0:  21%|██▏       | 78/363 [00:03<00:11, 24.51it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:10, 27.61it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:11, 24.76it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:08, 31.12it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:09, 28.87it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:10, 24.32it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:12, 21.26it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:09, 26.41it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:10, 23.95it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 29.88it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 28.35it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 30.51it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:08, 28.13it/s]
Loading 0:  38%|███▊      | 137/363 [00:05<00:07, 28.42it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:09, 24.45it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:09, 23.02it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:09, 22.30it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:07, 28.94it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:07, 28.11it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:06, 30.81it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:06, 28.99it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 30.21it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 27.92it/s]
Loading 0:  50%|████▉     | 181/363 [00:06<00:06, 27.25it/s]
Loading 0:  51%|█████     | 184/363 [00:07<00:08, 20.57it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:08, 21.61it/s]
Loading 0:  53%|█████▎    | 192/363 [00:07<00:06, 25.44it/s]
Loading 0:  54%|█████▎    | 195/363 [00:07<00:07, 23.53it/s]
Loading 0:  55%|█████▌    | 201/363 [00:07<00:05, 28.26it/s]
Loading 0:  56%|█████▌    | 204/363 [00:07<00:06, 25.66it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:05, 30.24it/s]
Loading 0:  59%|█████▉    | 214/363 [00:08<00:05, 28.62it/s]
Loading 0:  60%|██████    | 218/363 [00:08<00:05, 28.32it/s]
Loading 0:  61%|██████▏   | 223/363 [00:08<00:05, 25.08it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:05, 23.44it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:06, 22.10it/s]
Loading 0:  65%|██████▌   | 237/363 [00:08<00:04, 28.64it/s]
Loading 0:  66%|██████▋   | 241/363 [00:09<00:04, 27.50it/s]
Loading 0:  68%|██████▊   | 246/363 [00:09<00:03, 29.97it/s]
Loading 0:  69%|██████▉   | 250/363 [00:09<00:03, 28.75it/s]
Loading 0:  70%|███████   | 255/363 [00:09<00:03, 31.22it/s]
Loading 0:  71%|███████▏  | 259/363 [00:09<00:03, 28.86it/s]
Loading 0:  72%|███████▏  | 263/363 [00:09<00:04, 24.07it/s]
Loading 0:  73%|███████▎  | 266/363 [00:10<00:04, 21.05it/s]
Loading 0:  75%|███████▌  | 273/363 [00:10<00:03, 27.88it/s]
Loading 0:  76%|███████▋  | 277/363 [00:10<00:03, 27.05it/s]
Loading 0:  78%|███████▊  | 282/363 [00:10<00:02, 29.02it/s]
Loading 0:  79%|███████▉  | 286/363 [00:10<00:02, 27.75it/s]
Loading 0:  80%|████████  | 291/363 [00:10<00:02, 30.02it/s]
Loading 0:  81%|████████▏ | 295/363 [00:11<00:02, 27.66it/s]
Loading 0:  82%|████████▏ | 299/363 [00:11<00:02, 27.52it/s]
Loading 0:  84%|████████▎ | 304/363 [00:11<00:02, 23.92it/s]
Loading 0:  85%|████████▍ | 307/363 [00:11<00:02, 22.44it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 21.70it/s]
Loading 0:  87%|████████▋ | 316/363 [00:11<00:01, 26.89it/s]
Loading 0:  88%|████████▊ | 320/363 [00:12<00:01, 24.29it/s]
Loading 0:  90%|█████████ | 327/363 [00:12<00:01, 29.94it/s]
Loading 0:  91%|█████████ | 331/363 [00:12<00:01, 28.46it/s]
Loading 0:  93%|█████████▎| 336/363 [00:12<00:00, 30.49it/s]
Loading 0:  94%|█████████▎| 340/363 [00:12<00:00, 28.83it/s]
Loading 0:  95%|█████████▍| 344/363 [00:19<00:09,  1.95it/s]
Loading 0:  96%|█████████▌| 348/363 [00:20<00:05,  2.62it/s]
Loading 0:  97%|█████████▋| 353/363 [00:20<00:02,  3.77it/s]
Loading 0:  98%|█████████▊| 357/363 [00:20<00:01,  4.84it/s]
                                                            
Job rica40325-10-14dpo-v12-mkmlizer completed after 125.49s with status: succeeded
Stopping job with name rica40325-10-14dpo-v12-mkmlizer
Pipeline stage MKMLizer completed in 125.96s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rica40325-10-14dpo-v12
Waiting for inference service rica40325-10-14dpo-v12 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service rica40325-10-14dpo-v12 ready after 373.15593218803406s
Pipeline stage MKMLDeployer completed in 373.84s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8682663440704346s
Received healthy response to inference request in 1.357412576675415s
Received healthy response to inference request in 1.8393571376800537s
Received healthy response to inference request in 1.3314001560211182s
Received healthy response to inference request in 1.3178296089172363s
5 requests
0 failed requests
5th percentile: 1.3205437183380127
10th percentile: 1.323257827758789
20th percentile: 1.3286860466003418
30th percentile: 1.3366026401519775
40th percentile: 1.3470076084136964
50th percentile: 1.357412576675415
60th percentile: 1.5501904010772705
70th percentile: 1.7429682254791259
80th percentile: 1.8451389789581298
90th percentile: 1.8567026615142823
95th percentile: 1.8624845027923584
99th percentile: 1.8671099758148193
mean time: 1.5428531646728516
Pipeline stage StressChecker completed in 9.42s
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 0.71s
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
rica40325-10-14dpo_v12 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 2461.03s
Shutdown handler de-registered
rica40325-10-14dpo_v12 status is now inactive due to auto deactivation removed underperforming models
rica40325-10-14dpo_v12 status is now torndown due to DeploymentManager action