developer_uid: AlexCuadron
submission_id: alexcuadron-dpo-task-vio_v1
model_name: alexcuadron-dpo-task-vio_v1
model_group: AlexCuadron/dpo_task_vio
status: torndown
timestamp: 2025-03-24T20:53:17+00:00
num_battles: 7057
num_wins: 3562
celo_rating: 1284.14
family_friendly_score: 0.5754
family_friendly_standard_error: 0.0069902051472041935
submission_type: basic
model_repo: AlexCuadron/dpo_task_vio
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.5988944713886293, 'latency_mean': 1.6696507942676544, 'latency_p50': 1.6649243831634521, 'latency_p90': 1.842864751815796}, {'batch_size': 3, 'throughput': 1.0871970132005104, 'latency_mean': 2.751158881187439, 'latency_p50': 2.7750186920166016, 'latency_p90': 3.04758677482605}, {'batch_size': 5, 'throughput': 1.3182017837742568, 'latency_mean': 3.784980670213699, 'latency_p50': 3.761689305305481, 'latency_p90': 4.245812177658081}, {'batch_size': 6, 'throughput': 1.3837120083797914, 'latency_mean': 4.312361341714859, 'latency_p50': 4.301011562347412, 'latency_p90': 4.864251446723938}, {'batch_size': 8, 'throughput': 1.419200919824577, 'latency_mean': 5.58778251171112, 'latency_p50': 5.583984851837158, 'latency_p90': 6.27246823310852}, {'batch_size': 10, 'throughput': 1.4723941455968346, 'latency_mean': 6.727107938528061, 'latency_p50': 6.76520311832428, 'latency_p90': 7.559374451637268}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: alexcuadron-dpo-task-vio_v1
is_internal_developer: False
language_model: AlexCuadron/dpo_task_vio
model_size: 13B
ranking_group: single
throughput_3p7s: 1.31
us_pacific_date: 2025-03-24
win_ratio: 0.5047470596570781
generation_params: {'temperature': 0.7, 'top_p': 0.85, 'min_p': 0.1, 'top_k': 40, 'presence_penalty': 0.1, 'frequency_penalty': 0.4, '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-task-vio-v1-mkmlizer
Waiting for job on alexcuadron-dpo-task-vio-v1-mkmlizer to finish
alexcuadron-dpo-task-vio-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexcuadron-dpo-task-vio-v1-mkmlizer: ║ _____ __ __ ║
alexcuadron-dpo-task-vio-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
alexcuadron-dpo-task-vio-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
alexcuadron-dpo-task-vio-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
alexcuadron-dpo-task-vio-v1-mkmlizer: ║ /___/ ║
alexcuadron-dpo-task-vio-v1-mkmlizer: ║ ║
alexcuadron-dpo-task-vio-v1-mkmlizer: ║ Version: 0.12.8 ║
alexcuadron-dpo-task-vio-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
alexcuadron-dpo-task-vio-v1-mkmlizer: ║ https://mk1.ai ║
alexcuadron-dpo-task-vio-v1-mkmlizer: ║ ║
alexcuadron-dpo-task-vio-v1-mkmlizer: ║ The license key for the current software has been verified as ║
alexcuadron-dpo-task-vio-v1-mkmlizer: ║ belonging to: ║
alexcuadron-dpo-task-vio-v1-mkmlizer: ║ ║
alexcuadron-dpo-task-vio-v1-mkmlizer: ║ Chai Research Corp. ║
alexcuadron-dpo-task-vio-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
alexcuadron-dpo-task-vio-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
alexcuadron-dpo-task-vio-v1-mkmlizer: ║ ║
alexcuadron-dpo-task-vio-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alexcuadron-dpo-task-vio-v1-mkmlizer: Downloaded to shared memory in 42.738s
alexcuadron-dpo-task-vio-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpg2lrxcf6, device:0
alexcuadron-dpo-task-vio-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alexcuadron-dpo-task-vio-v1-mkmlizer: quantized model in 35.827s
alexcuadron-dpo-task-vio-v1-mkmlizer: Processed model AlexCuadron/dpo_task_vio in 78.566s
alexcuadron-dpo-task-vio-v1-mkmlizer: creating bucket guanaco-mkml-models
alexcuadron-dpo-task-vio-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexcuadron-dpo-task-vio-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexcuadron-dpo-task-vio-v1
alexcuadron-dpo-task-vio-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alexcuadron-dpo-task-vio-v1/config.json
alexcuadron-dpo-task-vio-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alexcuadron-dpo-task-vio-v1/special_tokens_map.json
alexcuadron-dpo-task-vio-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexcuadron-dpo-task-vio-v1/tokenizer_config.json
alexcuadron-dpo-task-vio-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexcuadron-dpo-task-vio-v1/tokenizer.json
alexcuadron-dpo-task-vio-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alexcuadron-dpo-task-vio-v1/flywheel_model.0.safetensors
alexcuadron-dpo-task-vio-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 2/363 [00:06<18:12, 3.03s/it] Loading 0: 2%|▏ | 6/363 [00:06<04:50, 1.23it/s] Loading 0: 4%|▎ | 13/363 [00:06<01:43, 3.38it/s] Loading 0: 5%|▍ | 18/363 [00:06<01:04, 5.38it/s] Loading 0: 6%|▋ | 23/363 [00:06<00:42, 7.95it/s] Loading 0: 8%|▊ | 29/363 [00:06<00:29, 11.52it/s] Loading 0: 9%|▉ | 34/363 [00:06<00:21, 15.00it/s] Loading 0: 11%|█ | 40/363 [00:07<00:18, 17.20it/s] Loading 0: 12%|█▏ | 44/363 [00:07<00:16, 19.75it/s] Loading 0: 14%|█▍ | 50/363 [00:07<00:12, 25.49it/s] Loading 0: 15%|█▌ | 56/363 [00:07<00:10, 29.68it/s] Loading 0: 17%|█▋ | 61/363 [00:07<00:09, 32.18it/s] Loading 0: 19%|█▊ | 68/363 [00:07<00:07, 38.53it/s] Loading 0: 20%|██ | 74/363 [00:07<00:07, 37.68it/s] Loading 0: 22%|██▏ | 79/363 [00:07<00:07, 39.27it/s] Loading 0: 24%|██▎ | 86/363 [00:08<00:06, 44.84it/s] Loading 0: 25%|██▌ | 92/363 [00:08<00:06, 43.04it/s] Loading 0: 27%|██▋ | 97/363 [00:08<00:06, 43.32it/s] Loading 0: 29%|██▊ | 104/363 [00:08<00:05, 48.28it/s] Loading 0: 30%|███ | 110/363 [00:08<00:05, 46.31it/s] Loading 0: 32%|███▏ | 115/363 [00:08<00:05, 44.35it/s] Loading 0: 33%|███▎ | 121/363 [00:08<00:07, 34.18it/s] Loading 0: 34%|███▍ | 125/363 [00:09<00:06, 34.17it/s] Loading 0: 36%|███▌ | 131/363 [00:09<00:06, 38.08it/s] Loading 0: 37%|███▋ | 136/363 [00:09<00:05, 40.02it/s] Loading 0: 39%|███▉ | 141/363 [00:09<00:06, 34.97it/s] Loading 0: 41%|████ | 148/363 [00:09<00:05, 42.20it/s] Loading 0: 42%|████▏ | 153/363 [00:09<00:04, 42.11it/s] Loading 0: 44%|████▎ | 158/363 [00:09<00:04, 42.61it/s] Loading 0: 45%|████▍ | 163/363 [00:09<00:04, 44.21it/s] Loading 0: 46%|████▋ | 168/363 [00:10<00:05, 36.75it/s] Loading 0: 48%|████▊ | 176/363 [00:10<00:04, 43.74it/s] Loading 0: 50%|████▉ | 181/363 [00:10<00:04, 43.77it/s] Loading 0: 51%|█████ | 186/363 [00:10<00:04, 37.88it/s] Loading 0: 53%|█████▎ | 194/363 [00:10<00:03, 45.82it/s] Loading 0: 55%|█████▌ | 200/363 [00:10<00:03, 44.88it/s] Loading 0: 56%|█████▋ | 205/363 [00:11<00:05, 31.47it/s] Loading 0: 58%|█████▊ | 212/363 [00:11<00:04, 37.43it/s] Loading 0: 60%|██████ | 218/363 [00:11<00:03, 38.07it/s] Loading 0: 61%|██████▏ | 223/363 [00:11<00:03, 38.15it/s] Loading 0: 63%|██████▎ | 230/363 [00:11<00:03, 43.74it/s] Loading 0: 65%|██████▌ | 236/363 [00:11<00:02, 43.81it/s] Loading 0: 66%|██████▋ | 241/363 [00:11<00:02, 42.20it/s] Loading 0: 68%|██████▊ | 247/363 [00:11<00:02, 45.79it/s] Loading 0: 69%|██████▉ | 252/363 [00:12<00:02, 46.00it/s] Loading 0: 71%|███████ | 257/363 [00:12<00:02, 46.61it/s] Loading 0: 72%|███████▏ | 263/363 [00:12<00:02, 44.38it/s] Loading 0: 74%|███████▍ | 268/363 [00:12<00:02, 43.05it/s] Loading 0: 76%|███████▌ | 275/363 [00:12<00:01, 47.73it/s] Loading 0: 77%|███████▋ | 281/363 [00:12<00:01, 46.14it/s] Loading 0: 79%|███████▉ | 286/363 [00:13<00:02, 31.70it/s] Loading 0: 80%|████████ | 292/363 [00:13<00:01, 36.74it/s] Loading 0: 82%|████████▏ | 297/363 [00:13<00:01, 37.71it/s] Loading 0: 83%|████████▎ | 302/363 [00:13<00:01, 39.33it/s] Loading 0: 85%|████████▍ | 307/363 [00:13<00:01, 41.18it/s] Loading 0: 86%|████████▌ | 312/363 [00:13<00:01, 36.88it/s] Loading 0: 88%|████████▊ | 320/363 [00:13<00:00, 45.04it/s] Loading 0: 90%|████████▉ | 326/363 [00:13<00:00, 43.95it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:00, 42.37it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:00, 47.12it/s] Loading 0: 95%|█████████▍| 344/363 [00:14<00:00, 45.97it/s] Loading 0: 96%|█████████▌| 349/363 [00:14<00:00, 44.43it/s] Loading 0: 98%|█████████▊| 355/363 [00:14<00:00, 47.97it/s] Loading 0: 99%|█████████▉| 360/363 [00:14<00:00, 46.17it/s]
Job alexcuadron-dpo-task-vio-v1-mkmlizer completed after 103.93s with status: succeeded
Stopping job with name alexcuadron-dpo-task-vio-v1-mkmlizer
Pipeline stage MKMLizer completed in 104.37s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.33s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service alexcuadron-dpo-task-vio-v1
Waiting for inference service alexcuadron-dpo-task-vio-v1 to be ready
Inference service alexcuadron-dpo-task-vio-v1 ready after 100.34210014343262s
Pipeline stage MKMLDeployer completed in 100.73s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.420309066772461s
Received healthy response to inference request in 1.8308556079864502s
Received healthy response to inference request in 1.7114005088806152s
Received healthy response to inference request in 1.737865924835205s
Received healthy response to inference request in 1.6374659538269043s
5 requests
0 failed requests
5th percentile: 1.6522528648376464
10th percentile: 1.6670397758483886
20th percentile: 1.696613597869873
30th percentile: 1.7166935920715332
40th percentile: 1.7272797584533692
50th percentile: 1.737865924835205
60th percentile: 1.775061798095703
70th percentile: 1.812257671356201
80th percentile: 1.9487462997436524
90th percentile: 2.1845276832580565
95th percentile: 2.3024183750152587
99th percentile: 2.3967309284210203
mean time: 1.867579412460327
Pipeline stage StressChecker completed in 10.47s
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 0.63s
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 0.57s
Shutdown handler de-registered
alexcuadron-dpo-task-vio_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
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service alexcuadron-dpo-task-vio-v1-profiler
Waiting for inference service alexcuadron-dpo-task-vio-v1-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 2514.14s
Shutdown handler de-registered
alexcuadron-dpo-task-vio_v1 status is now inactive due to auto deactivation removed underperforming models
alexcuadron-dpo-task-vio_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1