developer_uid: BBChicago
submission_id: bbchicago-violet-kto-ep2_v1
model_name: violet-kto-ep1
model_group: BBChicago/violet-kto-ep2
status: torndown
timestamp: 2025-04-27T02:26:00+00:00
num_battles: 11988
num_wins: 5652
celo_rating: 1267.1
family_friendly_score: 0.5262
family_friendly_standard_error: 0.007061353411351113
submission_type: basic
model_repo: BBChicago/violet-kto-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': 0.6084611670684599, 'latency_mean': 1.6434134197235108, 'latency_p50': 1.643103837966919, 'latency_p90': 1.821312141418457}, {'batch_size': 3, 'throughput': 1.1131035890211993, 'latency_mean': 2.6886697614192965, 'latency_p50': 2.6739262342453003, 'latency_p90': 2.956689143180847}, {'batch_size': 5, 'throughput': 1.3321258300536956, 'latency_mean': 3.7228416812419893, 'latency_p50': 3.732411742210388, 'latency_p90': 4.146107864379883}, {'batch_size': 6, 'throughput': 1.408743178878532, 'latency_mean': 4.236349790096283, 'latency_p50': 4.199803709983826, 'latency_p90': 4.716851902008057}, {'batch_size': 8, 'throughput': 1.482723085321547, 'latency_mean': 5.355708131790161, 'latency_p50': 5.337317585945129, 'latency_p90': 6.107659006118774}, {'batch_size': 10, 'throughput': 1.523988777882452, 'latency_mean': 6.516730587482453, 'latency_p50': 6.469109535217285, 'latency_p90': 7.474870109558106}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: violet-kto-ep1
is_internal_developer: False
language_model: BBChicago/violet-kto-ep2
model_size: 13B
ranking_group: single
throughput_3p7s: 1.34
us_pacific_date: 2025-04-26
win_ratio: 0.47147147147147145
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-kto-ep2-v1-mkmlizer
Waiting for job on bbchicago-violet-kto-ep2-v1-mkmlizer to finish
bbchicago-violet-kto-ep2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-violet-kto-ep2-v1-mkmlizer: ║ _____ __ __ ║
bbchicago-violet-kto-ep2-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
bbchicago-violet-kto-ep2-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
bbchicago-violet-kto-ep2-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
bbchicago-violet-kto-ep2-v1-mkmlizer: ║ /___/ ║
bbchicago-violet-kto-ep2-v1-mkmlizer: ║ ║
bbchicago-violet-kto-ep2-v1-mkmlizer: ║ Version: 0.12.8 ║
bbchicago-violet-kto-ep2-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
bbchicago-violet-kto-ep2-v1-mkmlizer: ║ https://mk1.ai ║
bbchicago-violet-kto-ep2-v1-mkmlizer: ║ ║
bbchicago-violet-kto-ep2-v1-mkmlizer: ║ The license key for the current software has been verified as ║
bbchicago-violet-kto-ep2-v1-mkmlizer: ║ belonging to: ║
bbchicago-violet-kto-ep2-v1-mkmlizer: ║ ║
bbchicago-violet-kto-ep2-v1-mkmlizer: ║ Chai Research Corp. ║
bbchicago-violet-kto-ep2-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
bbchicago-violet-kto-ep2-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
bbchicago-violet-kto-ep2-v1-mkmlizer: ║ ║
bbchicago-violet-kto-ep2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-violet-kto-ep2-v1-mkmlizer: Downloaded to shared memory in 50.225s
bbchicago-violet-kto-ep2-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpp0urtml7, device:0
bbchicago-violet-kto-ep2-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
bbchicago-violet-kto-ep2-v1-mkmlizer: quantized model in 36.534s
bbchicago-violet-kto-ep2-v1-mkmlizer: Processed model BBChicago/violet-kto-ep2 in 86.760s
bbchicago-violet-kto-ep2-v1-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-violet-kto-ep2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-violet-kto-ep2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-violet-kto-ep2-v1
bbchicago-violet-kto-ep2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-violet-kto-ep2-v1/config.json
bbchicago-violet-kto-ep2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-violet-kto-ep2-v1/special_tokens_map.json
bbchicago-violet-kto-ep2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-violet-kto-ep2-v1/tokenizer_config.json
bbchicago-violet-kto-ep2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-violet-kto-ep2-v1/tokenizer.json
bbchicago-violet-kto-ep2-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-violet-kto-ep2-v1/flywheel_model.0.safetensors
bbchicago-violet-kto-ep2-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:11, 30.99it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:06, 52.07it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 45.74it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:07, 43.11it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 48.90it/s] Loading 0: 10%|█ | 37/363 [00:00<00:07, 46.40it/s] Loading 0: 12%|█▏ | 42/363 [00:00<00:07, 45.63it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:06, 51.18it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 48.02it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:08, 35.04it/s] Loading 0: 18%|█▊ | 66/363 [00:01<00:08, 35.59it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 39.57it/s] Loading 0: 21%|██ | 77/363 [00:01<00:06, 41.65it/s] Loading 0: 23%|██▎ | 82/363 [00:01<00:07, 36.36it/s] Loading 0: 25%|██▍ | 89/363 [00:02<00:06, 43.36it/s] Loading 0: 26%|██▌ | 94/363 [00:02<00:06, 43.60it/s] Loading 0: 27%|██▋ | 99/363 [00:02<00:05, 45.14it/s] Loading 0: 29%|██▉ | 105/363 [00:02<00:05, 44.26it/s] Loading 0: 31%|███ | 112/363 [00:02<00:05, 48.01it/s] Loading 0: 32%|███▏ | 117/363 [00:02<00:05, 46.28it/s] Loading 0: 34%|███▍ | 123/363 [00:02<00:05, 44.42it/s] Loading 0: 35%|███▌ | 128/363 [00:02<00:05, 43.43it/s] Loading 0: 37%|███▋ | 134/363 [00:03<00:04, 46.14it/s] Loading 0: 38%|███▊ | 139/363 [00:03<00:04, 46.07it/s] Loading 0: 40%|███▉ | 144/363 [00:03<00:07, 27.93it/s] Loading 0: 41%|████ | 149/363 [00:03<00:07, 30.49it/s] Loading 0: 43%|████▎ | 156/363 [00:03<00:05, 38.22it/s] Loading 0: 44%|████▍ | 161/363 [00:03<00:05, 39.97it/s] Loading 0: 46%|████▌ | 166/363 [00:03<00:04, 41.86it/s] Loading 0: 47%|████▋ | 171/363 [00:04<00:04, 42.70it/s] Loading 0: 48%|████▊ | 176/363 [00:04<00:05, 36.05it/s] Loading 0: 50%|█████ | 183/363 [00:04<00:04, 43.67it/s] Loading 0: 52%|█████▏ | 188/363 [00:04<00:04, 39.84it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:04, 41.14it/s] Loading 0: 55%|█████▍ | 198/363 [00:04<00:03, 42.96it/s] Loading 0: 56%|█████▌ | 203/363 [00:04<00:04, 36.22it/s] Loading 0: 58%|█████▊ | 210/363 [00:05<00:03, 43.91it/s] Loading 0: 59%|█████▉ | 215/363 [00:05<00:03, 43.86it/s] Loading 0: 61%|██████ | 221/363 [00:05<00:02, 47.50it/s] Loading 0: 63%|██████▎ | 227/363 [00:05<00:04, 31.73it/s] Loading 0: 64%|██████▍ | 232/363 [00:05<00:04, 31.97it/s] Loading 0: 65%|██████▌ | 237/363 [00:05<00:03, 34.47it/s] Loading 0: 66%|██████▋ | 241/363 [00:05<00:03, 34.58it/s] Loading 0: 68%|██████▊ | 247/363 [00:06<00:02, 39.37it/s] Loading 0: 69%|██████▉ | 252/363 [00:06<00:02, 41.37it/s] Loading 0: 71%|███████ | 257/363 [00:06<00:02, 35.89it/s] Loading 0: 73%|███████▎ | 265/363 [00:06<00:02, 44.05it/s] Loading 0: 74%|███████▍ | 270/363 [00:06<00:02, 45.34it/s] Loading 0: 76%|███████▌ | 275/363 [00:06<00:02, 37.79it/s] Loading 0: 78%|███████▊ | 282/363 [00:06<00:01, 44.87it/s] Loading 0: 79%|███████▉ | 287/363 [00:07<00:01, 43.70it/s] Loading 0: 80%|████████ | 292/363 [00:07<00:01, 42.85it/s] Loading 0: 82%|████████▏ | 298/363 [00:07<00:01, 41.96it/s] Loading 0: 83%|████████▎ | 303/363 [00:07<00:01, 43.86it/s] Loading 0: 85%|████████▍ | 308/363 [00:14<00:22, 2.44it/s] Loading 0: 86%|████████▌ | 312/363 [00:14<00:16, 3.15it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:08, 5.19it/s] Loading 0: 90%|████████▉ | 326/363 [00:14<00:05, 7.10it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:03, 9.14it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:01, 12.97it/s] Loading 0: 94%|█████████▍| 343/363 [00:15<00:01, 15.91it/s] Loading 0: 96%|█████████▌| 348/363 [00:15<00:00, 17.80it/s] Loading 0: 98%|█████████▊| 356/363 [00:15<00:00, 25.10it/s] Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 28.70it/s]
Job bbchicago-violet-kto-ep2-v1-mkmlizer completed after 114.8s with status: succeeded
Stopping job with name bbchicago-violet-kto-ep2-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.31s
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-kto-ep2-v1
Waiting for inference service bbchicago-violet-kto-ep2-v1 to be ready
Inference service bbchicago-violet-kto-ep2-v1 ready after 130.643874168396s
Pipeline stage MKMLDeployer completed in 131.18s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2245054244995117s
Received healthy response to inference request in 1.9337091445922852s
Received healthy response to inference request in 1.7326459884643555s
Received healthy response to inference request in 1.7283825874328613s
Received healthy response to inference request in 1.7783496379852295s
5 requests
0 failed requests
5th percentile: 1.7292352676391602
10th percentile: 1.730087947845459
20th percentile: 1.7317933082580566
30th percentile: 1.7417867183685303
40th percentile: 1.7600681781768799
50th percentile: 1.7783496379852295
60th percentile: 1.8404934406280518
70th percentile: 1.902637243270874
80th percentile: 1.9918684005737306
90th percentile: 2.1081869125366213
95th percentile: 2.1663461685180665
99th percentile: 2.2128735733032228
mean time: 1.8795185565948487
Pipeline stage StressChecker completed in 10.77s
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 0.88s
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 0.72s
Shutdown handler de-registered
bbchicago-violet-kto-ep2_v1 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 0.09s
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 4604.78s
Shutdown handler de-registered
bbchicago-violet-kto-ep2_v1 status is now inactive due to auto deactivation removed underperforming models
bbchicago-violet-kto-ep2_v1 status is now torndown due to DeploymentManager action