developer_uid: AlexCuadron
submission_id: alexcuadron-dpo-task-og-v3_v1
model_name: alexcuadron-dpo-task-og-v3_v1
model_group: AlexCuadron/dpo_task_og_
status: torndown
timestamp: 2025-03-24T22:20:50+00:00
num_battles: 8129
num_wins: 4037
celo_rating: 1278.75
family_friendly_score: 0.5782
family_friendly_standard_error: 0.006984049828000943
submission_type: basic
model_repo: AlexCuadron/dpo_task_og_v3
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.5922587413996653, 'latency_mean': 1.688381026983261, 'latency_p50': 1.680543065071106, 'latency_p90': 1.8632225275039673}, {'batch_size': 3, 'throughput': 1.0721473169038607, 'latency_mean': 2.7930978560447692, 'latency_p50': 2.7867108583450317, 'latency_p90': 3.0737648248672484}, {'batch_size': 5, 'throughput': 1.2981897066211365, 'latency_mean': 3.827454820871353, 'latency_p50': 3.803905725479126, 'latency_p90': 4.21690788269043}, {'batch_size': 6, 'throughput': 1.3575624109941042, 'latency_mean': 4.386230062246323, 'latency_p50': 4.3989139795303345, 'latency_p90': 4.87763741016388}, {'batch_size': 8, 'throughput': 1.4199291876711624, 'latency_mean': 5.596762882471085, 'latency_p50': 5.542199492454529, 'latency_p90': 6.373008561134339}, {'batch_size': 10, 'throughput': 1.4623511623166003, 'latency_mean': 6.783049018383026, 'latency_p50': 6.776715397834778, 'latency_p90': 7.708333802223206}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: alexcuadron-dpo-task-og-v3_v1
is_internal_developer: False
language_model: AlexCuadron/dpo_task_og_v3
model_size: 13B
ranking_group: single
throughput_3p7s: 1.28
us_pacific_date: 2025-03-24
win_ratio: 0.496617050067659
generation_params: {'temperature': 1.0, 'top_p': 0.9, 'min_p': 0.1, 'top_k': 40, 'presence_penalty': 0.1, 'frequency_penalty': 0.0, 'stopping_words': ['</s>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "<s>{bot_name}'s Persona: {memory}\n", 'prompt_template': '{prompt}', 'bot_template': '{bot_name}: {message}</s>', 'user_template': '[INST]{user_name}: {message}[/INST]', '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 alexcuadron-dpo-task-og-v3-v1-mkmlizer
Waiting for job on alexcuadron-dpo-task-og-v3-v1-mkmlizer to finish
alexcuadron-dpo-task-og-v3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexcuadron-dpo-task-og-v3-v1-mkmlizer: ║ _____ __ __ ║
alexcuadron-dpo-task-og-v3-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
alexcuadron-dpo-task-og-v3-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
alexcuadron-dpo-task-og-v3-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
alexcuadron-dpo-task-og-v3-v1-mkmlizer: ║ /___/ ║
alexcuadron-dpo-task-og-v3-v1-mkmlizer: ║ ║
alexcuadron-dpo-task-og-v3-v1-mkmlizer: ║ Version: 0.12.8 ║
alexcuadron-dpo-task-og-v3-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
alexcuadron-dpo-task-og-v3-v1-mkmlizer: ║ https://mk1.ai ║
alexcuadron-dpo-task-og-v3-v1-mkmlizer: ║ ║
alexcuadron-dpo-task-og-v3-v1-mkmlizer: ║ The license key for the current software has been verified as ║
alexcuadron-dpo-task-og-v3-v1-mkmlizer: ║ belonging to: ║
alexcuadron-dpo-task-og-v3-v1-mkmlizer: ║ ║
alexcuadron-dpo-task-og-v3-v1-mkmlizer: ║ Chai Research Corp. ║
alexcuadron-dpo-task-og-v3-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
alexcuadron-dpo-task-og-v3-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
alexcuadron-dpo-task-og-v3-v1-mkmlizer: ║ ║
alexcuadron-dpo-task-og-v3-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alexcuadron-dpo-task-og-v3-v1-mkmlizer: Downloaded to shared memory in 41.555s
alexcuadron-dpo-task-og-v3-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpkvd09809, device:0
alexcuadron-dpo-task-og-v3-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alexcuadron-dpo-task-og-v3-v1-mkmlizer: quantized model in 36.052s
alexcuadron-dpo-task-og-v3-v1-mkmlizer: Processed model AlexCuadron/dpo_task_og_v3 in 77.607s
alexcuadron-dpo-task-og-v3-v1-mkmlizer: creating bucket guanaco-mkml-models
alexcuadron-dpo-task-og-v3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexcuadron-dpo-task-og-v3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexcuadron-dpo-task-og-v3-v1
alexcuadron-dpo-task-og-v3-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alexcuadron-dpo-task-og-v3-v1/config.json
alexcuadron-dpo-task-og-v3-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alexcuadron-dpo-task-og-v3-v1/special_tokens_map.json
alexcuadron-dpo-task-og-v3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexcuadron-dpo-task-og-v3-v1/tokenizer_config.json
alexcuadron-dpo-task-og-v3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexcuadron-dpo-task-og-v3-v1/tokenizer.json
alexcuadron-dpo-task-og-v3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alexcuadron-dpo-task-og-v3-v1/flywheel_model.0.safetensors
alexcuadron-dpo-task-og-v3-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 2/363 [00:06<18:32, 3.08s/it] Loading 0: 2%|▏ | 6/363 [00:06<04:56, 1.21it/s] Loading 0: 4%|▎ | 13/363 [00:06<01:45, 3.32it/s] Loading 0: 5%|▍ | 18/363 [00:06<01:05, 5.27it/s] Loading 0: 6%|▋ | 23/363 [00:06<00:43, 7.80it/s] Loading 0: 8%|▊ | 29/363 [00:06<00:29, 11.27it/s] Loading 0: 9%|▉ | 34/363 [00:06<00:22, 14.52it/s] Loading 0: 11%|█ | 40/363 [00:07<00:19, 16.28it/s] Loading 0: 12%|█▏ | 44/363 [00:07<00:16, 18.77it/s] Loading 0: 14%|█▍ | 50/363 [00:07<00:12, 24.17it/s] Loading 0: 15%|█▌ | 56/363 [00:07<00:10, 28.28it/s] Loading 0: 17%|█▋ | 61/363 [00:07<00:09, 30.76it/s] Loading 0: 19%|█▊ | 68/363 [00:07<00:07, 37.35it/s] Loading 0: 20%|██ | 73/363 [00:07<00:07, 40.05it/s] Loading 0: 21%|██▏ | 78/363 [00:08<00:07, 36.82it/s] Loading 0: 24%|██▎ | 86/363 [00:08<00:06, 44.71it/s] Loading 0: 25%|██▌ | 91/363 [00:08<00:05, 45.53it/s] Loading 0: 26%|██▋ | 96/363 [00:08<00:06, 40.22it/s] Loading 0: 29%|██▊ | 104/363 [00:08<00:05, 47.84it/s] Loading 0: 30%|███ | 110/363 [00:08<00:05, 45.40it/s] Loading 0: 32%|███▏ | 115/363 [00:08<00:05, 44.05it/s] Loading 0: 33%|███▎ | 121/363 [00:09<00:07, 33.55it/s] Loading 0: 34%|███▍ | 125/363 [00:09<00:07, 33.28it/s] Loading 0: 36%|███▌ | 131/363 [00:09<00:06, 37.60it/s] Loading 0: 38%|███▊ | 137/363 [00:09<00:05, 39.27it/s] Loading 0: 39%|███▉ | 142/363 [00:09<00:05, 38.94it/s] Loading 0: 41%|████ | 148/363 [00:09<00:05, 42.72it/s] Loading 0: 42%|████▏ | 153/363 [00:09<00:04, 43.48it/s] Loading 0: 44%|████▎ | 158/363 [00:09<00:04, 44.81it/s] Loading 0: 45%|████▌ | 164/363 [00:10<00:04, 43.85it/s] Loading 0: 47%|████▋ | 169/363 [00:10<00:04, 42.17it/s] Loading 0: 48%|████▊ | 176/363 [00:10<00:03, 46.81it/s] Loading 0: 50%|█████ | 182/363 [00:10<00:04, 44.45it/s] Loading 0: 52%|█████▏ | 187/363 [00:10<00:04, 43.30it/s] Loading 0: 53%|█████▎ | 194/363 [00:10<00:03, 47.84it/s] Loading 0: 55%|█████▌ | 200/363 [00:10<00:03, 46.32it/s] Loading 0: 56%|█████▋ | 205/363 [00:11<00:04, 32.01it/s] Loading 0: 58%|█████▊ | 212/363 [00:11<00:03, 38.06it/s] Loading 0: 60%|██████ | 218/363 [00:11<00:03, 38.58it/s] Loading 0: 61%|██████▏ | 223/363 [00:11<00:03, 38.03it/s] Loading 0: 63%|██████▎ | 230/363 [00:11<00:03, 43.49it/s] Loading 0: 65%|██████▌ | 236/363 [00:11<00:02, 43.43it/s] Loading 0: 66%|██████▋ | 241/363 [00:11<00:02, 41.30it/s] Loading 0: 68%|██████▊ | 247/363 [00:12<00:02, 45.62it/s] Loading 0: 69%|██████▉ | 252/363 [00:12<00:02, 46.26it/s] Loading 0: 71%|███████ | 257/363 [00:12<00:02, 46.25it/s] Loading 0: 72%|███████▏ | 263/363 [00:12<00:02, 43.72it/s] Loading 0: 74%|███████▍ | 268/363 [00:12<00:02, 42.04it/s] Loading 0: 75%|███████▌ | 274/363 [00:12<00:01, 46.41it/s] Loading 0: 77%|███████▋ | 279/363 [00:12<00:01, 45.99it/s] Loading 0: 78%|███████▊ | 284/363 [00:13<00:02, 32.58it/s] Loading 0: 80%|███████▉ | 289/363 [00:13<00:02, 35.86it/s] Loading 0: 81%|████████ | 294/363 [00:13<00:02, 33.47it/s] Loading 0: 83%|████████▎ | 301/363 [00:13<00:01, 41.10it/s] Loading 0: 84%|████████▍ | 306/363 [00:13<00:01, 42.39it/s] Loading 0: 86%|████████▌ | 311/363 [00:13<00:01, 43.89it/s] Loading 0: 87%|████████▋ | 317/363 [00:13<00:01, 43.13it/s] Loading 0: 89%|████████▊ | 322/363 [00:13<00:00, 42.36it/s] Loading 0: 90%|█████████ | 328/363 [00:14<00:00, 46.14it/s] Loading 0: 92%|█████████▏| 333/363 [00:14<00:00, 46.45it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:00, 47.13it/s] Loading 0: 95%|█████████▍| 344/363 [00:14<00:00, 45.61it/s] Loading 0: 96%|█████████▌| 349/363 [00:14<00:00, 42.35it/s] Loading 0: 98%|█████████▊| 355/363 [00:14<00:00, 46.74it/s] Loading 0: 99%|█████████▉| 360/363 [00:14<00:00, 46.38it/s]
Job alexcuadron-dpo-task-og-v3-v1-mkmlizer completed after 104.48s with status: succeeded
Stopping job with name alexcuadron-dpo-task-og-v3-v1-mkmlizer
Pipeline stage MKMLizer completed in 104.95s
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 alexcuadron-dpo-task-og-v3-v1
Waiting for inference service alexcuadron-dpo-task-og-v3-v1 to be ready
Inference service alexcuadron-dpo-task-og-v3-v1 ready after 100.37186932563782s
Pipeline stage MKMLDeployer completed in 101.14s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.569441080093384s
Received healthy response to inference request in 1.703641414642334s
Received healthy response to inference request in 1.763390302658081s
Received healthy response to inference request in 1.8108201026916504s
Received healthy response to inference request in 1.869260311126709s
5 requests
0 failed requests
5th percentile: 1.7155911922454834
10th percentile: 1.7275409698486328
20th percentile: 1.7514405250549316
30th percentile: 1.772876262664795
40th percentile: 1.7918481826782227
50th percentile: 1.8108201026916504
60th percentile: 1.834196186065674
70th percentile: 1.8575722694396972
80th percentile: 2.009296464920044
90th percentile: 2.289368772506714
95th percentile: 2.4294049263000486
99th percentile: 2.541433849334717
mean time: 1.9433106422424316
Pipeline stage StressChecker completed in 11.05s
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 0.72s
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 0.84s
Shutdown handler de-registered
alexcuadron-dpo-task-og-v3_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 2678.38s
Shutdown handler de-registered
alexcuadron-dpo-task-og-v3_v1 status is now inactive due to auto deactivation removed underperforming models
alexcuadron-dpo-task-og-v3_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1