developer_uid: AlexCuadron
submission_id: alexcuadron-dpo-slurp-r_29528_v2
model_name: alexcuadron-dpo-slurp-r_29528_v2
model_group: AlexCuadron/dpo_slurp_ro
status: torndown
timestamp: 2025-03-24T19:05:08+00:00
num_battles: 7108
num_wins: 3670
celo_rating: 1288.1
family_friendly_score: 0.5833999999999999
family_friendly_standard_error: 0.006972007458401059
submission_type: basic
model_repo: AlexCuadron/dpo_slurp_roleplay_v2
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6111847829178471, 'latency_mean': 1.63610649228096, 'latency_p50': 1.631601095199585, 'latency_p90': 1.8230171203613281}, {'batch_size': 3, 'throughput': 1.1228985721073084, 'latency_mean': 2.667837485074997, 'latency_p50': 2.6747671365737915, 'latency_p90': 2.994176650047302}, {'batch_size': 5, 'throughput': 1.3479688508133965, 'latency_mean': 3.698704878091812, 'latency_p50': 3.6678953170776367, 'latency_p90': 4.220932388305664}, {'batch_size': 6, 'throughput': 1.4197055150811886, 'latency_mean': 4.19326220035553, 'latency_p50': 4.183186769485474, 'latency_p90': 4.69407513141632}, {'batch_size': 8, 'throughput': 1.4810297084837694, 'latency_mean': 5.370724651813507, 'latency_p50': 5.339153528213501, 'latency_p90': 6.096632194519043}, {'batch_size': 10, 'throughput': 1.5114769497903875, 'latency_mean': 6.560920120477676, 'latency_p50': 6.616560697555542, 'latency_p90': 7.352737855911255}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: alexcuadron-dpo-slurp-r_29528_v2
is_internal_developer: False
language_model: AlexCuadron/dpo_slurp_roleplay_v2
model_size: 13B
ranking_group: single
throughput_3p7s: 1.35
us_pacific_date: 2025-03-24
win_ratio: 0.516319639842431
generation_params: {'temperature': 1.0, 'top_p': 0.9, 'min_p': 0.1, 'top_k': 40, 'presence_penalty': 0.1, 'frequency_penalty': 0.1, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', '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 alexcuadron-dpo-slurp-r-29528-v2-mkmlizer
Waiting for job on alexcuadron-dpo-slurp-r-29528-v2-mkmlizer to finish
alexcuadron-dpo-slurp-r-29528-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexcuadron-dpo-slurp-r-29528-v2-mkmlizer: ║ _____ __ __ ║
alexcuadron-dpo-slurp-r-29528-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
alexcuadron-dpo-slurp-r-29528-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
alexcuadron-dpo-slurp-r-29528-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
alexcuadron-dpo-slurp-r-29528-v2-mkmlizer: ║ /___/ ║
alexcuadron-dpo-slurp-r-29528-v2-mkmlizer: ║ ║
alexcuadron-dpo-slurp-r-29528-v2-mkmlizer: ║ Version: 0.12.8 ║
alexcuadron-dpo-slurp-r-29528-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
alexcuadron-dpo-slurp-r-29528-v2-mkmlizer: ║ https://mk1.ai ║
alexcuadron-dpo-slurp-r-29528-v2-mkmlizer: ║ ║
alexcuadron-dpo-slurp-r-29528-v2-mkmlizer: ║ The license key for the current software has been verified as ║
alexcuadron-dpo-slurp-r-29528-v2-mkmlizer: ║ belonging to: ║
alexcuadron-dpo-slurp-r-29528-v2-mkmlizer: ║ ║
alexcuadron-dpo-slurp-r-29528-v2-mkmlizer: ║ Chai Research Corp. ║
alexcuadron-dpo-slurp-r-29528-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
alexcuadron-dpo-slurp-r-29528-v2-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
alexcuadron-dpo-slurp-r-29528-v2-mkmlizer: ║ ║
alexcuadron-dpo-slurp-r-29528-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alexcuadron-dpo-slurp-r-29528-v2-mkmlizer: Downloaded to shared memory in 38.607s
alexcuadron-dpo-slurp-r-29528-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp3m9cym62, device:0
alexcuadron-dpo-slurp-r-29528-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alexcuadron-dpo-slurp-r-29528-v2-mkmlizer: quantized model in 36.287s
alexcuadron-dpo-slurp-r-29528-v2-mkmlizer: Processed model AlexCuadron/dpo_slurp_roleplay_v2 in 74.894s
alexcuadron-dpo-slurp-r-29528-v2-mkmlizer: creating bucket guanaco-mkml-models
alexcuadron-dpo-slurp-r-29528-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexcuadron-dpo-slurp-r-29528-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexcuadron-dpo-slurp-r-29528-v2
alexcuadron-dpo-slurp-r-29528-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexcuadron-dpo-slurp-r-29528-v2/tokenizer_config.json
alexcuadron-dpo-slurp-r-29528-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexcuadron-dpo-slurp-r-29528-v2/tokenizer.json
alexcuadron-dpo-slurp-r-29528-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alexcuadron-dpo-slurp-r-29528-v2/flywheel_model.0.safetensors
alexcuadron-dpo-slurp-r-29528-v2-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 2/363 [00:06<18:27, 3.07s/it] Loading 0: 2%|▏ | 6/363 [00:06<04:55, 1.21it/s] Loading 0: 3%|▎ | 11/363 [00:06<02:10, 2.70it/s] Loading 0: 4%|▍ | 15/363 [00:06<01:22, 4.21it/s] Loading 0: 6%|▋ | 23/363 [00:06<00:40, 8.36it/s] Loading 0: 8%|▊ | 29/363 [00:06<00:28, 11.70it/s] Loading 0: 9%|▉ | 34/363 [00:06<00:22, 14.83it/s] Loading 0: 11%|█ | 40/363 [00:07<00:19, 16.45it/s] Loading 0: 12%|█▏ | 44/363 [00:07<00:17, 18.75it/s] Loading 0: 13%|█▎ | 49/363 [00:07<00:13, 23.12it/s] Loading 0: 15%|█▍ | 53/363 [00:07<00:12, 25.20it/s] Loading 0: 16%|█▌ | 58/363 [00:07<00:10, 29.64it/s] Loading 0: 17%|█▋ | 63/363 [00:07<00:09, 32.39it/s] Loading 0: 19%|█▊ | 68/363 [00:07<00:08, 34.95it/s] Loading 0: 20%|██ | 73/363 [00:08<00:07, 38.04it/s] Loading 0: 21%|██▏ | 78/363 [00:08<00:08, 35.56it/s] Loading 0: 24%|██▎ | 86/363 [00:08<00:06, 44.35it/s] Loading 0: 25%|██▌ | 92/363 [00:08<00:06, 43.89it/s] Loading 0: 27%|██▋ | 97/363 [00:08<00:06, 43.02it/s] Loading 0: 29%|██▊ | 104/363 [00:08<00:05, 47.77it/s] Loading 0: 30%|███ | 109/363 [00:08<00:05, 47.22it/s] Loading 0: 31%|███▏ | 114/363 [00:09<00:06, 37.95it/s] Loading 0: 33%|███▎ | 121/363 [00:09<00:07, 32.88it/s] Loading 0: 34%|███▍ | 125/363 [00:09<00:07, 33.28it/s] Loading 0: 36%|███▌ | 131/363 [00:09<00:06, 37.59it/s] Loading 0: 37%|███▋ | 136/363 [00:09<00:05, 40.33it/s] Loading 0: 39%|███▉ | 141/363 [00:09<00:06, 36.06it/s] Loading 0: 41%|████ | 148/363 [00:09<00:05, 42.50it/s] Loading 0: 42%|████▏ | 153/363 [00:10<00:04, 43.23it/s] Loading 0: 44%|████▎ | 158/363 [00:10<00:04, 44.62it/s] Loading 0: 45%|████▌ | 164/363 [00:10<00:04, 43.31it/s] Loading 0: 47%|████▋ | 169/363 [00:10<00:04, 40.41it/s] Loading 0: 48%|████▊ | 175/363 [00:10<00:04, 44.74it/s] Loading 0: 50%|████▉ | 180/363 [00:10<00:04, 44.88it/s] Loading 0: 51%|█████ | 185/363 [00:10<00:04, 44.35it/s] Loading 0: 52%|█████▏ | 190/363 [00:10<00:03, 45.30it/s] Loading 0: 54%|█████▎ | 195/363 [00:11<00:04, 37.90it/s] Loading 0: 56%|█████▌ | 202/363 [00:11<00:04, 33.00it/s] Loading 0: 57%|█████▋ | 206/363 [00:11<00:04, 33.32it/s] Loading 0: 58%|█████▊ | 212/363 [00:11<00:04, 37.73it/s] Loading 0: 60%|██████ | 218/363 [00:11<00:03, 39.41it/s] Loading 0: 61%|██████▏ | 223/363 [00:11<00:03, 39.68it/s] Loading 0: 63%|██████▎ | 229/363 [00:11<00:03, 43.64it/s] Loading 0: 64%|██████▍ | 234/363 [00:11<00:02, 44.05it/s] Loading 0: 66%|██████▌ | 239/363 [00:12<00:02, 45.04it/s] Loading 0: 67%|██████▋ | 245/363 [00:12<00:02, 43.01it/s] Loading 0: 69%|██████▉ | 250/363 [00:12<00:02, 41.13it/s] Loading 0: 71%|███████ | 256/363 [00:12<00:02, 45.10it/s] Loading 0: 72%|███████▏ | 261/363 [00:12<00:02, 45.38it/s] Loading 0: 73%|███████▎ | 266/363 [00:12<00:02, 45.93it/s] Loading 0: 75%|███████▍ | 271/363 [00:12<00:01, 46.44it/s] Loading 0: 76%|███████▌ | 276/363 [00:13<00:02, 35.66it/s] Loading 0: 78%|███████▊ | 283/363 [00:13<00:02, 30.49it/s] Loading 0: 79%|███████▉ | 287/363 [00:13<00:02, 31.20it/s] Loading 0: 81%|████████ | 293/363 [00:13<00:01, 35.77it/s] Loading 0: 82%|████████▏ | 298/363 [00:13<00:01, 38.44it/s] Loading 0: 83%|████████▎ | 303/363 [00:13<00:01, 34.55it/s] Loading 0: 85%|████████▌ | 310/363 [00:13<00:01, 41.83it/s] Loading 0: 87%|████████▋ | 315/363 [00:14<00:01, 43.54it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:00, 45.05it/s] Loading 0: 90%|████████▉ | 326/363 [00:14<00:00, 44.28it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:00, 43.50it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:00, 48.22it/s] Loading 0: 95%|█████████▍| 344/363 [00:14<00:00, 47.14it/s] Loading 0: 96%|█████████▌| 349/363 [00:14<00:00, 45.87it/s] Loading 0: 98%|█████████▊| 355/363 [00:14<00:00, 49.15it/s] Loading 0: 99%|█████████▉| 360/363 [00:14<00:00, 48.69it/s]
Job alexcuadron-dpo-slurp-r-29528-v2-mkmlizer completed after 93.68s with status: succeeded
Stopping job with name alexcuadron-dpo-slurp-r-29528-v2-mkmlizer
Pipeline stage MKMLizer completed in 94.18s
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-slurp-r-29528-v2
Waiting for inference service alexcuadron-dpo-slurp-r-29528-v2 to be ready
Inference service alexcuadron-dpo-slurp-r-29528-v2 ready after 80.26881742477417s
Pipeline stage MKMLDeployer completed in 80.77s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3194689750671387s
Received healthy response to inference request in 1.6207525730133057s
Received healthy response to inference request in 1.6390712261199951s
Received healthy response to inference request in 1.6569406986236572s
Received healthy response to inference request in 1.6632041931152344s
5 requests
0 failed requests
5th percentile: 1.6244163036346435
10th percentile: 1.6280800342559814
20th percentile: 1.6354074954986573
30th percentile: 1.6426451206207275
40th percentile: 1.6497929096221924
50th percentile: 1.6569406986236572
60th percentile: 1.6594460964202882
70th percentile: 1.661951494216919
80th percentile: 1.7944571495056154
90th percentile: 2.056963062286377
95th percentile: 2.1882160186767576
99th percentile: 2.2932183837890623
mean time: 1.7798875331878663
Pipeline stage StressChecker completed in 10.04s
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 0.69s
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 0.71s
Shutdown handler de-registered
alexcuadron-dpo-slurp-r_29528_v2 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
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service alexcuadron-dpo-slurp-r-29528-v2-profiler
Waiting for inference service alexcuadron-dpo-slurp-r-29528-v2-profiler to be ready
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 2768.18s
Shutdown handler de-registered
alexcuadron-dpo-slurp-r_29528_v2 status is now inactive due to auto deactivation removed underperforming models
alexcuadron-dpo-slurp-r_29528_v2 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1