developer_uid: AlexCuadron
submission_id: alexcuadron-dpo-slurp-mm_v1
model_name: alexcuadron-dpo-slurp-mm_v1
model_group: AlexCuadron/dpo_slurp_mm
status: torndown
timestamp: 2025-03-24T23:25:45+00:00
num_battles: 6231
num_wins: 3162
celo_rating: 1284.81
family_friendly_score: 0.5756
family_friendly_standard_error: 0.00698977310075227
submission_type: basic
model_repo: AlexCuadron/dpo_slurp_mm
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.5797018333974524, 'latency_mean': 1.7249507045745849, 'latency_p50': 1.7134660482406616, 'latency_p90': 1.9053309917449952}, {'batch_size': 3, 'throughput': 1.027936152234182, 'latency_mean': 2.9137323820590972, 'latency_p50': 2.911058783531189, 'latency_p90': 3.1823451280593873}, {'batch_size': 5, 'throughput': 1.22956850733397, 'latency_mean': 4.044236642122269, 'latency_p50': 4.05099892616272, 'latency_p90': 4.50897581577301}, {'batch_size': 6, 'throughput': 1.266694969338094, 'latency_mean': 4.717014545202256, 'latency_p50': 4.732118606567383, 'latency_p90': 5.321658301353454}, {'batch_size': 8, 'throughput': 1.3289767579936789, 'latency_mean': 5.974642170667648, 'latency_p50': 5.936069488525391, 'latency_p90': 6.7859635829925535}, {'batch_size': 10, 'throughput': 1.358678601174352, 'latency_mean': 7.307860823869706, 'latency_p50': 7.355417966842651, 'latency_p90': 8.43140377998352}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: alexcuadron-dpo-slurp-mm_v1
is_internal_developer: False
language_model: AlexCuadron/dpo_slurp_mm
model_size: 13B
ranking_group: single
throughput_3p7s: 1.19
us_pacific_date: 2025-03-24
win_ratio: 0.5074626865671642
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-slurp-mm-v1-mkmlizer
Waiting for job on alexcuadron-dpo-slurp-mm-v1-mkmlizer to finish
alexcuadron-dpo-slurp-mm-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexcuadron-dpo-slurp-mm-v1-mkmlizer: ║ _____ __ __ ║
alexcuadron-dpo-slurp-mm-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
alexcuadron-dpo-slurp-mm-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
alexcuadron-dpo-slurp-mm-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
alexcuadron-dpo-slurp-mm-v1-mkmlizer: ║ /___/ ║
alexcuadron-dpo-slurp-mm-v1-mkmlizer: ║ ║
alexcuadron-dpo-slurp-mm-v1-mkmlizer: ║ Version: 0.12.8 ║
alexcuadron-dpo-slurp-mm-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
alexcuadron-dpo-slurp-mm-v1-mkmlizer: ║ https://mk1.ai ║
alexcuadron-dpo-slurp-mm-v1-mkmlizer: ║ ║
alexcuadron-dpo-slurp-mm-v1-mkmlizer: ║ The license key for the current software has been verified as ║
alexcuadron-dpo-slurp-mm-v1-mkmlizer: ║ belonging to: ║
alexcuadron-dpo-slurp-mm-v1-mkmlizer: ║ ║
alexcuadron-dpo-slurp-mm-v1-mkmlizer: ║ Chai Research Corp. ║
alexcuadron-dpo-slurp-mm-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
alexcuadron-dpo-slurp-mm-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
alexcuadron-dpo-slurp-mm-v1-mkmlizer: ║ ║
alexcuadron-dpo-slurp-mm-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alexcuadron-dpo-slurp-mm-v1-mkmlizer: Downloaded to shared memory in 41.685s
alexcuadron-dpo-slurp-mm-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpjwit0ikr, device:0
alexcuadron-dpo-slurp-mm-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alexcuadron-dpo-slurp-mm-v1-mkmlizer: quantized model in 35.693s
alexcuadron-dpo-slurp-mm-v1-mkmlizer: Processed model AlexCuadron/dpo_slurp_mm in 77.378s
alexcuadron-dpo-slurp-mm-v1-mkmlizer: creating bucket guanaco-mkml-models
alexcuadron-dpo-slurp-mm-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexcuadron-dpo-slurp-mm-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexcuadron-dpo-slurp-mm-v1
alexcuadron-dpo-slurp-mm-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alexcuadron-dpo-slurp-mm-v1/config.json
alexcuadron-dpo-slurp-mm-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alexcuadron-dpo-slurp-mm-v1/special_tokens_map.json
alexcuadron-dpo-slurp-mm-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexcuadron-dpo-slurp-mm-v1/tokenizer_config.json
alexcuadron-dpo-slurp-mm-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexcuadron-dpo-slurp-mm-v1/tokenizer.json
alexcuadron-dpo-slurp-mm-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alexcuadron-dpo-slurp-mm-v1/flywheel_model.0.safetensors
alexcuadron-dpo-slurp-mm-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 2/363 [00:06<18:11, 3.02s/it] Loading 0: 2%|▏ | 6/363 [00:06<04:49, 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, 11.50it/s] Loading 0: 9%|▉ | 34/363 [00:06<00:22, 14.86it/s] Loading 0: 11%|█ | 40/363 [00:07<00:18, 17.30it/s] Loading 0: 12%|█▏ | 44/363 [00:07<00:15, 20.01it/s] Loading 0: 14%|█▍ | 50/363 [00:07<00:12, 25.58it/s] Loading 0: 15%|█▌ | 55/363 [00:07<00:10, 29.76it/s] Loading 0: 17%|█▋ | 60/363 [00:07<00:10, 29.30it/s] Loading 0: 19%|█▊ | 68/363 [00:07<00:07, 38.08it/s] Loading 0: 20%|██ | 74/363 [00:07<00:07, 38.28it/s] Loading 0: 22%|██▏ | 79/363 [00:07<00:07, 38.98it/s] Loading 0: 24%|██▎ | 86/363 [00:08<00:06, 44.72it/s] Loading 0: 25%|██▌ | 92/363 [00:08<00:06, 43.08it/s] Loading 0: 27%|██▋ | 97/363 [00:08<00:06, 42.98it/s] Loading 0: 29%|██▊ | 104/363 [00:08<00:05, 47.49it/s] Loading 0: 30%|███ | 110/363 [00:08<00:05, 44.93it/s] Loading 0: 32%|███▏ | 115/363 [00:08<00:05, 42.87it/s] Loading 0: 33%|███▎ | 121/363 [00:08<00:06, 35.07it/s] Loading 0: 34%|███▍ | 125/363 [00:09<00:06, 34.89it/s] Loading 0: 36%|███▌ | 130/363 [00:09<00:06, 38.21it/s] Loading 0: 37%|███▋ | 135/363 [00:09<00:05, 39.45it/s] Loading 0: 39%|███▊ | 140/363 [00:09<00:05, 40.64it/s] Loading 0: 40%|████ | 146/363 [00:09<00:05, 39.86it/s] Loading 0: 42%|████▏ | 151/363 [00:09<00:05, 39.87it/s] Loading 0: 43%|████▎ | 157/363 [00:09<00:04, 44.80it/s] Loading 0: 45%|████▍ | 162/363 [00:09<00:04, 45.04it/s] Loading 0: 46%|████▌ | 167/363 [00:09<00:04, 44.21it/s] Loading 0: 48%|████▊ | 173/363 [00:10<00:04, 42.24it/s] Loading 0: 49%|████▉ | 178/363 [00:10<00:04, 41.95it/s] Loading 0: 51%|█████ | 184/363 [00:10<00:03, 46.24it/s] Loading 0: 52%|█████▏ | 189/363 [00:10<00:03, 44.71it/s] Loading 0: 53%|█████▎ | 194/363 [00:10<00:03, 44.87it/s] Loading 0: 55%|█████▌ | 200/363 [00:10<00:03, 40.93it/s] Loading 0: 56%|█████▋ | 205/363 [00:11<00:05, 29.47it/s] Loading 0: 58%|█████▊ | 211/363 [00:11<00:04, 34.84it/s] Loading 0: 60%|█████▉ | 216/363 [00:11<00:04, 36.49it/s] Loading 0: 61%|██████ | 221/363 [00:11<00:03, 37.63it/s] Loading 0: 63%|██████▎ | 227/363 [00:11<00:03, 37.76it/s] Loading 0: 64%|██████▍ | 232/363 [00:11<00:03, 38.23it/s] Loading 0: 66%|██████▌ | 238/363 [00:11<00:02, 42.45it/s] Loading 0: 67%|██████▋ | 243/363 [00:11<00:02, 42.48it/s] Loading 0: 68%|██████▊ | 248/363 [00:12<00:02, 43.11it/s] Loading 0: 70%|██████▉ | 253/363 [00:12<00:02, 43.31it/s] Loading 0: 71%|███████ | 258/363 [00:12<00:02, 35.97it/s] Loading 0: 73%|███████▎ | 265/363 [00:12<00:02, 43.44it/s] Loading 0: 74%|███████▍ | 270/363 [00:12<00:02, 44.11it/s] Loading 0: 76%|███████▌ | 275/363 [00:12<00:02, 43.33it/s] Loading 0: 77%|███████▋ | 280/363 [00:12<00:01, 43.85it/s] Loading 0: 79%|███████▊ | 285/363 [00:13<00:02, 26.68it/s] Loading 0: 80%|████████ | 292/363 [00:13<00:02, 33.60it/s] Loading 0: 82%|████████▏ | 297/363 [00:13<00:01, 35.85it/s] Loading 0: 83%|████████▎ | 302/363 [00:13<00:01, 38.00it/s] Loading 0: 85%|████████▍ | 308/363 [00:13<00:01, 37.14it/s] Loading 0: 86%|████████▌ | 313/363 [00:13<00:01, 37.02it/s] Loading 0: 88%|████████▊ | 319/363 [00:13<00:01, 41.35it/s] Loading 0: 89%|████████▉ | 324/363 [00:14<00:00, 41.21it/s] Loading 0: 91%|█████████ | 329/363 [00:14<00:00, 41.13it/s] Loading 0: 92%|█████████▏| 334/363 [00:14<00:00, 42.66it/s] Loading 0: 93%|█████████▎| 339/363 [00:14<00:00, 36.85it/s] Loading 0: 95%|█████████▌| 346/363 [00:14<00:00, 44.48it/s] Loading 0: 97%|█████████▋| 351/363 [00:14<00:00, 44.10it/s] Loading 0: 98%|█████████▊| 356/363 [00:14<00:00, 43.68it/s] Loading 0: 100%|█████████▉| 362/363 [00:14<00:00, 42.09it/s]
Job alexcuadron-dpo-slurp-mm-v1-mkmlizer completed after 236.58s with status: succeeded
Stopping job with name alexcuadron-dpo-slurp-mm-v1-mkmlizer
Pipeline stage MKMLizer completed in 237.04s
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-mm-v1
Waiting for inference service alexcuadron-dpo-slurp-mm-v1 to be ready
Failed to get response for submission jellywibble-tony-stark-_67676_v1: HTTPConnectionPool(host='jellywibble-tony-stark-67676-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission jellywibble-tony-stark-_67676_v1: HTTPConnectionPool(host='jellywibble-tony-stark-67676-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service alexcuadron-dpo-slurp-mm-v1 ready after 90.33252954483032s
Pipeline stage MKMLDeployer completed in 90.83s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.7029471397399902s
Received healthy response to inference request in 1.7498018741607666s
Received healthy response to inference request in 1.8053770065307617s
Received healthy response to inference request in 1.945784568786621s
Received healthy response to inference request in 1.675119400024414s
5 requests
0 failed requests
5th percentile: 1.6900558948516846
10th percentile: 1.7049923896789552
20th percentile: 1.734865379333496
30th percentile: 1.7609169006347656
40th percentile: 1.7831469535827638
50th percentile: 1.8053770065307617
60th percentile: 1.8615400314331054
70th percentile: 1.9177030563354491
80th percentile: 2.097217082977295
90th percentile: 2.4000821113586426
95th percentile: 2.5515146255493164
99th percentile: 2.6726606369018553
mean time: 1.9758059978485107
Pipeline stage StressChecker completed in 11.16s
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 0.61s
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 0.61s
Shutdown handler de-registered
alexcuadron-dpo-slurp-mm_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4133.38s
Shutdown handler de-registered
alexcuadron-dpo-slurp-mm_v1 status is now inactive due to auto deactivation removed underperforming models
alexcuadron-dpo-slurp-mm_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1