bbchicago-violet-dpo-ep2

developer_uid: BBChicago

submission_id: bbchicago-violet-dpo-ep2_v1

model_name: violet-dpo-ep2

model_group: BBChicago/violet-dpo-ep2

status: torndown

timestamp: 2025-04-23T08:04:20+00:00

num_battles: 9249

num_wins: 4509

celo_rating: 1280.7

family_friendly_score: 0.5324

family_friendly_standard_error: 0.007056206346189147

submission_type: basic

model_repo: BBChicago/violet-dpo-ep2

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6029577476643567, 'latency_mean': 1.6584006977081298, 'latency_p50': 1.6549999713897705, 'latency_p90': 1.828636932373047}, {'batch_size': 3, 'throughput': 1.0990231562239279, 'latency_mean': 2.722442083358765, 'latency_p50': 2.699396252632141, 'latency_p90': 3.020970678329468}, {'batch_size': 5, 'throughput': 1.3142883565488725, 'latency_mean': 3.7849925005435945, 'latency_p50': 3.798152446746826, 'latency_p90': 4.226125979423523}, {'batch_size': 6, 'throughput': 1.3814011125147696, 'latency_mean': 4.319975879192352, 'latency_p50': 4.338313817977905, 'latency_p90': 4.908697938919067}, {'batch_size': 8, 'throughput': 1.4308775535385663, 'latency_mean': 5.550913455486298, 'latency_p50': 5.575395584106445, 'latency_p90': 6.29377977848053}, {'batch_size': 10, 'throughput': 1.4812665526448379, 'latency_mean': 6.699676027297974, 'latency_p50': 6.704235672950745, 'latency_p90': 7.615387797355652}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: violet-dpo-ep2

is_internal_developer: False

language_model: BBChicago/violet-dpo-ep2

model_size: 13B

ranking_group: single

throughput_3p7s: 1.31

us_pacific_date: 2025-04-23

win_ratio: 0.48751216347713267

generation_params: {'temperature': 0.85, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 60, 'presence_penalty': 0.1, 'frequency_penalty': 0.1, 'stopping_words': ['\n', '<s>', '[INST]', '[/INST]', '</s>', 'You:'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': "<s>[INST]{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n[/INST]</s>', 'bot_template': '{bot_name}: {message}</s>\n', 'user_template': '<s>[INST]{user_name}: {message}[/INST]\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 bbchicago-violet-dpo-ep2-v1-mkmlizer
Waiting for job on bbchicago-violet-dpo-ep2-v1-mkmlizer to finish
bbchicago-violet-dpo-ep2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-violet-dpo-ep2-v1-mkmlizer: ║     _____            __           __                                ║
bbchicago-violet-dpo-ep2-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
bbchicago-violet-dpo-ep2-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
bbchicago-violet-dpo-ep2-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
bbchicago-violet-dpo-ep2-v1-mkmlizer: ║       /___/                                                         ║
bbchicago-violet-dpo-ep2-v1-mkmlizer: ║                                                                     ║
bbchicago-violet-dpo-ep2-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
bbchicago-violet-dpo-ep2-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
bbchicago-violet-dpo-ep2-v1-mkmlizer: ║  https://mk1.ai                                                     ║
bbchicago-violet-dpo-ep2-v1-mkmlizer: ║                                                                     ║
bbchicago-violet-dpo-ep2-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
bbchicago-violet-dpo-ep2-v1-mkmlizer: ║  belonging to:                                                      ║
bbchicago-violet-dpo-ep2-v1-mkmlizer: ║                                                                     ║
bbchicago-violet-dpo-ep2-v1-mkmlizer: ║  Chai Research Corp.                                                ║
bbchicago-violet-dpo-ep2-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
bbchicago-violet-dpo-ep2-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
bbchicago-violet-dpo-ep2-v1-mkmlizer: ║                                                                     ║
bbchicago-violet-dpo-ep2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-violet-dpo-ep2-v1-mkmlizer: Downloaded to shared memory in 40.194s
bbchicago-violet-dpo-ep2-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmptlpht07u, device:0
bbchicago-violet-dpo-ep2-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
bbchicago-violet-dpo-ep2-v1-mkmlizer: quantized model in 36.557s
bbchicago-violet-dpo-ep2-v1-mkmlizer: Processed model BBChicago/violet-dpo-ep2 in 76.751s
bbchicago-violet-dpo-ep2-v1-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-violet-dpo-ep2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-violet-dpo-ep2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-violet-dpo-ep2-v1
bbchicago-violet-dpo-ep2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-violet-dpo-ep2-v1/config.json
bbchicago-violet-dpo-ep2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-violet-dpo-ep2-v1/special_tokens_map.json
bbchicago-violet-dpo-ep2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-violet-dpo-ep2-v1/tokenizer_config.json
bbchicago-violet-dpo-ep2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-violet-dpo-ep2-v1/tokenizer.json
bbchicago-violet-dpo-ep2-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-violet-dpo-ep2-v1/flywheel_model.0.safetensors
bbchicago-violet-dpo-ep2-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 30.07it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 49.63it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 44.92it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 42.22it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 48.97it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 43.25it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 40.55it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:07, 43.77it/s]
Loading 0:  15%|█▍        | 53/363 [00:01<00:07, 42.29it/s]
Loading 0:  16%|█▌        | 58/363 [00:01<00:07, 42.05it/s]
Loading 0:  17%|█▋        | 63/363 [00:01<00:10, 27.64it/s]
Loading 0:  18%|█▊        | 67/363 [00:01<00:09, 29.89it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:08, 32.99it/s]
Loading 0:  21%|██        | 77/363 [00:02<00:07, 36.71it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:08, 33.18it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:06, 39.96it/s]
Loading 0:  26%|██▌       | 94/363 [00:02<00:06, 38.94it/s]
Loading 0:  27%|██▋       | 99/363 [00:02<00:06, 39.58it/s]
Loading 0:  29%|██▊       | 104/363 [00:02<00:06, 40.27it/s]
Loading 0:  30%|███       | 109/363 [00:02<00:06, 41.03it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:07, 34.55it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:07, 32.24it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:05, 39.74it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 39.85it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 40.18it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:05, 42.08it/s]
Loading 0:  40%|███▉      | 145/363 [00:03<00:08, 26.43it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:07, 26.91it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:05, 34.56it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 36.96it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 38.37it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:04, 40.80it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 35.38it/s]
Loading 0:  51%|█████     | 184/363 [00:04<00:04, 43.57it/s]
Loading 0:  52%|█████▏    | 189/363 [00:04<00:03, 44.46it/s]
Loading 0:  53%|█████▎    | 194/363 [00:05<00:04, 36.73it/s]
Loading 0:  55%|█████▌    | 201/363 [00:05<00:03, 42.80it/s]
Loading 0:  57%|█████▋    | 206/363 [00:05<00:03, 40.68it/s]
Loading 0:  58%|█████▊    | 211/363 [00:05<00:03, 40.24it/s]
Loading 0:  60%|█████▉    | 216/363 [00:05<00:03, 41.80it/s]
Loading 0:  61%|██████    | 221/363 [00:05<00:03, 43.26it/s]
Loading 0:  62%|██████▏   | 226/363 [00:06<00:05, 26.36it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:04, 27.61it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 35.92it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 38.45it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:02, 39.47it/s]
Loading 0:  69%|██████▉   | 252/363 [00:06<00:02, 41.52it/s]
Loading 0:  71%|███████   | 257/363 [00:06<00:02, 36.34it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 44.41it/s]
Loading 0:  74%|███████▍  | 270/363 [00:07<00:02, 43.83it/s]
Loading 0:  76%|███████▌  | 275/363 [00:07<00:02, 37.19it/s]
Loading 0:  78%|███████▊  | 282/363 [00:07<00:01, 43.91it/s]
Loading 0:  79%|███████▉  | 287/363 [00:07<00:01, 43.28it/s]
Loading 0:  80%|████████  | 292/363 [00:07<00:01, 43.07it/s]
Loading 0:  82%|████████▏ | 297/363 [00:07<00:01, 44.35it/s]
Loading 0:  83%|████████▎ | 302/363 [00:07<00:01, 44.68it/s]
Loading 0:  85%|████████▍ | 307/363 [00:14<00:23,  2.39it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:15,  3.30it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:08,  5.36it/s]
Loading 0:  90%|████████▉ | 326/363 [00:15<00:05,  7.28it/s]
Loading 0:  91%|█████████ | 331/363 [00:15<00:03,  9.33it/s]
Loading 0:  93%|█████████▎| 338/363 [00:15<00:01, 13.27it/s]
Loading 0:  95%|█████████▍| 344/363 [00:15<00:01, 16.49it/s]
Loading 0:  96%|█████████▌| 349/363 [00:15<00:00, 19.40it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 25.43it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 27.69it/s]
                                                            
Job bbchicago-violet-dpo-ep2-v1-mkmlizer completed after 104.6s with status: succeeded
Stopping job with name bbchicago-violet-dpo-ep2-v1-mkmlizer
Pipeline stage MKMLizer completed in 105.09s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service bbchicago-violet-dpo-ep2-v1
Waiting for inference service bbchicago-violet-dpo-ep2-v1 to be ready
Inference service bbchicago-violet-dpo-ep2-v1 ready after 130.45010113716125s
Pipeline stage MKMLDeployer completed in 131.02s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.7507176399230957s
Received healthy response to inference request in 1.772657871246338s
Received healthy response to inference request in 1.6789915561676025s
Received healthy response to inference request in 1.7221159934997559s
Received healthy response to inference request in 1.769562005996704s
5 requests
0 failed requests
5th percentile: 1.6876164436340333
10th percentile: 1.6962413311004638
20th percentile: 1.713491106033325
30th percentile: 1.7316051959991454
40th percentile: 1.7505836009979248
50th percentile: 1.769562005996704
60th percentile: 1.7708003520965576
70th percentile: 1.7720386981964111
80th percentile: 1.9682698249816897
90th percentile: 2.3594937324523926
95th percentile: 2.555105686187744
99th percentile: 2.7115952491760256
mean time: 1.9388090133666993
Pipeline stage StressChecker completed in 11.02s
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 0.67s
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 0.65s
Shutdown handler de-registered
bbchicago-violet-dpo-ep2_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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2819.06s
Shutdown handler de-registered
bbchicago-violet-dpo-ep2_v1 status is now inactive due to auto deactivation removed underperforming models
bbchicago-violet-dpo-ep2_v1 status is now torndown due to DeploymentManager action