developer_uid: AlexCuadron
submission_id: alexcuadron-dpo-roleplay_v1
model_name: alexcuadron-dpo-roleplay_v1
model_group: AlexCuadron/dpo_roleplay
status: torndown
timestamp: 2025-03-24T16:37:20+00:00
num_battles: 10010
num_wins: 5078
celo_rating: 1283.12
family_friendly_score: 0.5856
family_friendly_standard_error: 0.006966672663474293
submission_type: basic
model_repo: AlexCuadron/dpo_roleplay
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6004421709880116, 'latency_mean': 1.6653728210926055, 'latency_p50': 1.6645560264587402, 'latency_p90': 1.8280701875686645}, {'batch_size': 3, 'throughput': 1.1089242759355407, 'latency_mean': 2.702726563215256, 'latency_p50': 2.673208713531494, 'latency_p90': 2.9957207918167112}, {'batch_size': 5, 'throughput': 1.334372881023342, 'latency_mean': 3.7274250388145447, 'latency_p50': 3.7544968128204346, 'latency_p90': 4.085845208168029}, {'batch_size': 6, 'throughput': 1.3871566557597501, 'latency_mean': 4.301294270753861, 'latency_p50': 4.310592293739319, 'latency_p90': 4.746545505523682}, {'batch_size': 8, 'throughput': 1.4559495554278779, 'latency_mean': 5.456825079917908, 'latency_p50': 5.499996900558472, 'latency_p90': 6.19315230846405}, {'batch_size': 10, 'throughput': 1.4792359378947424, 'latency_mean': 6.702624366283417, 'latency_p50': 6.726603031158447, 'latency_p90': 7.594120669364929}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: alexcuadron-dpo-roleplay_v1
is_internal_developer: False
language_model: AlexCuadron/dpo_roleplay
model_size: 13B
ranking_group: single
throughput_3p7s: 1.34
us_pacific_date: 2025-03-24
win_ratio: 0.5072927072927073
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-roleplay-v1-mkmlizer
Waiting for job on alexcuadron-dpo-roleplay-v1-mkmlizer to finish
alexcuadron-dpo-roleplay-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexcuadron-dpo-roleplay-v1-mkmlizer: ║ _____ __ __ ║
alexcuadron-dpo-roleplay-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
alexcuadron-dpo-roleplay-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
alexcuadron-dpo-roleplay-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
alexcuadron-dpo-roleplay-v1-mkmlizer: ║ /___/ ║
alexcuadron-dpo-roleplay-v1-mkmlizer: ║ ║
alexcuadron-dpo-roleplay-v1-mkmlizer: ║ Version: 0.12.8 ║
alexcuadron-dpo-roleplay-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
alexcuadron-dpo-roleplay-v1-mkmlizer: ║ https://mk1.ai ║
alexcuadron-dpo-roleplay-v1-mkmlizer: ║ ║
alexcuadron-dpo-roleplay-v1-mkmlizer: ║ The license key for the current software has been verified as ║
alexcuadron-dpo-roleplay-v1-mkmlizer: ║ belonging to: ║
alexcuadron-dpo-roleplay-v1-mkmlizer: ║ ║
alexcuadron-dpo-roleplay-v1-mkmlizer: ║ Chai Research Corp. ║
alexcuadron-dpo-roleplay-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
alexcuadron-dpo-roleplay-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
alexcuadron-dpo-roleplay-v1-mkmlizer: ║ ║
alexcuadron-dpo-roleplay-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alexcuadron-dpo-roleplay-v1-mkmlizer: Downloaded to shared memory in 42.522s
alexcuadron-dpo-roleplay-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp1juku84i, device:0
alexcuadron-dpo-roleplay-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission chaiml-exp112-nemo12b-sf_6117_v3: HTTPConnectionPool(host='chaiml-exp112-nemo12b-sf-6117-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
alexcuadron-dpo-roleplay-v1-mkmlizer: quantized model in 35.849s
alexcuadron-dpo-roleplay-v1-mkmlizer: Processed model AlexCuadron/dpo_roleplay in 78.371s
alexcuadron-dpo-roleplay-v1-mkmlizer: creating bucket guanaco-mkml-models
alexcuadron-dpo-roleplay-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexcuadron-dpo-roleplay-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexcuadron-dpo-roleplay-v1
alexcuadron-dpo-roleplay-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alexcuadron-dpo-roleplay-v1/config.json
alexcuadron-dpo-roleplay-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alexcuadron-dpo-roleplay-v1/special_tokens_map.json
alexcuadron-dpo-roleplay-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexcuadron-dpo-roleplay-v1/tokenizer_config.json
alexcuadron-dpo-roleplay-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexcuadron-dpo-roleplay-v1/tokenizer.json
alexcuadron-dpo-roleplay-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alexcuadron-dpo-roleplay-v1/flywheel_model.0.safetensors
alexcuadron-dpo-roleplay-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 2/363 [00:06<18:34, 3.09s/it] Loading 0: 2%|▏ | 6/363 [00:06<04:57, 1.20it/s] Loading 0: 4%|▎ | 13/363 [00:06<01:45, 3.31it/s] Loading 0: 5%|▌ | 19/363 [00:06<01:00, 5.68it/s] Loading 0: 7%|▋ | 24/363 [00:06<00:43, 7.71it/s] Loading 0: 9%|▊ | 31/363 [00:06<00:27, 12.01it/s] Loading 0: 10%|▉ | 36/363 [00:07<00:21, 14.92it/s] Loading 0: 11%|█▏ | 41/363 [00:07<00:20, 15.40it/s] Loading 0: 13%|█▎ | 46/363 [00:07<00:16, 19.30it/s] Loading 0: 14%|█▍ | 51/363 [00:07<00:14, 21.64it/s] Loading 0: 16%|█▋ | 59/363 [00:07<00:10, 29.69it/s] Loading 0: 18%|█▊ | 65/363 [00:07<00:09, 32.34it/s] Loading 0: 19%|█▉ | 70/363 [00:07<00:08, 33.83it/s] Loading 0: 21%|██ | 77/363 [00:08<00:07, 39.90it/s] Loading 0: 23%|██▎ | 83/363 [00:08<00:06, 40.87it/s] Loading 0: 24%|██▍ | 88/363 [00:08<00:06, 41.39it/s] Loading 0: 26%|██▌ | 95/363 [00:08<00:05, 46.83it/s] Loading 0: 28%|██▊ | 101/363 [00:08<00:05, 45.61it/s] Loading 0: 29%|██▉ | 106/363 [00:08<00:05, 44.48it/s] Loading 0: 31%|███ | 112/363 [00:08<00:05, 48.32it/s] Loading 0: 33%|███▎ | 118/363 [00:08<00:04, 49.42it/s] Loading 0: 34%|███▍ | 124/363 [00:09<00:07, 30.40it/s] Loading 0: 36%|███▌ | 130/363 [00:09<00:06, 35.72it/s] Loading 0: 37%|███▋ | 135/363 [00:09<00:05, 38.25it/s] Loading 0: 39%|███▊ | 140/363 [00:09<00:05, 40.62it/s] Loading 0: 40%|████ | 146/363 [00:09<00:05, 40.54it/s] Loading 0: 42%|████▏ | 151/363 [00:09<00:05, 40.40it/s] Loading 0: 44%|████▎ | 158/363 [00:10<00:04, 45.44it/s] Loading 0: 45%|████▌ | 164/363 [00:10<00:04, 43.98it/s] Loading 0: 47%|████▋ | 169/363 [00:10<00:04, 42.66it/s] Loading 0: 48%|████▊ | 175/363 [00:10<00:04, 46.58it/s] Loading 0: 50%|████▉ | 180/363 [00:10<00:04, 45.72it/s] Loading 0: 51%|█████ | 185/363 [00:10<00:03, 45.74it/s] Loading 0: 53%|█████▎ | 191/363 [00:10<00:03, 43.69it/s] Loading 0: 54%|█████▍ | 196/363 [00:10<00:03, 42.73it/s] Loading 0: 56%|█████▌ | 202/363 [00:11<00:04, 34.58it/s] Loading 0: 57%|█████▋ | 206/363 [00:11<00:04, 34.88it/s] Loading 0: 58%|█████▊ | 212/363 [00:11<00:03, 38.76it/s] Loading 0: 60%|██████ | 218/363 [00:11<00:03, 39.89it/s] Loading 0: 61%|██████▏ | 223/363 [00:11<00:03, 40.52it/s] Loading 0: 63%|██████▎ | 230/363 [00:11<00:02, 46.16it/s] Loading 0: 65%|██████▌ | 236/363 [00:11<00:02, 44.66it/s] Loading 0: 66%|██████▋ | 241/363 [00:12<00:02, 43.86it/s] Loading 0: 68%|██████▊ | 247/363 [00:12<00:02, 46.28it/s] Loading 0: 69%|██████▉ | 252/363 [00:12<00:02, 47.07it/s] Loading 0: 71%|███████ | 257/363 [00:12<00:02, 45.66it/s] Loading 0: 72%|███████▏ | 263/363 [00:12<00:02, 44.34it/s] Loading 0: 74%|███████▍ | 268/363 [00:12<00:02, 43.91it/s] Loading 0: 76%|███████▌ | 275/363 [00:12<00:01, 48.73it/s] Loading 0: 77%|███████▋ | 281/363 [00:12<00:01, 46.73it/s] Loading 0: 79%|███████▉ | 286/363 [00:13<00:02, 32.68it/s] Loading 0: 81%|████████ | 293/363 [00:13<00:01, 38.77it/s] Loading 0: 82%|████████▏ | 299/363 [00:13<00:01, 39.80it/s] Loading 0: 84%|████████▎ | 304/363 [00:13<00:01, 40.18it/s] Loading 0: 86%|████████▌ | 311/363 [00:13<00:01, 45.79it/s] Loading 0: 87%|████████▋ | 317/363 [00:13<00:01, 45.73it/s] Loading 0: 89%|████████▊ | 322/363 [00:13<00:00, 44.28it/s] Loading 0: 90%|█████████ | 328/363 [00:13<00:00, 47.80it/s] Loading 0: 92%|█████████▏| 333/363 [00:14<00:00, 46.30it/s] Loading 0: 93%|█████████▎| 339/363 [00:14<00:00, 42.38it/s] Loading 0: 95%|█████████▌| 346/363 [00:14<00:00, 48.49it/s] Loading 0: 97%|█████████▋| 352/363 [00:14<00:00, 49.71it/s] Loading 0: 99%|█████████▊| 358/363 [00:14<00:00, 43.48it/s]
Job alexcuadron-dpo-roleplay-v1-mkmlizer completed after 104.12s with status: succeeded
Stopping job with name alexcuadron-dpo-roleplay-v1-mkmlizer
Pipeline stage MKMLizer completed in 104.57s
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-roleplay-v1
Waiting for inference service alexcuadron-dpo-roleplay-v1 to be ready
Inference service alexcuadron-dpo-roleplay-v1 ready after 90.31736183166504s
Pipeline stage MKMLDeployer completed in 90.79s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3190560340881348s
Received healthy response to inference request in 1.6401894092559814s
Received healthy response to inference request in 1.5512967109680176s
Received healthy response to inference request in 1.5795109272003174s
Received healthy response to inference request in 1.6396067142486572s
5 requests
0 failed requests
5th percentile: 1.5569395542144775
10th percentile: 1.5625823974609374
20th percentile: 1.5738680839538575
30th percentile: 1.5915300846099854
40th percentile: 1.6155683994293213
50th percentile: 1.6396067142486572
60th percentile: 1.6398397922515868
70th percentile: 1.6400728702545166
80th percentile: 1.7759627342224122
90th percentile: 2.0475093841552736
95th percentile: 2.1832827091217037
99th percentile: 2.2919013690948487
mean time: 1.7459319591522218
Pipeline stage StressChecker completed in 9.85s
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 0.66s
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 0.62s
Shutdown handler de-registered
alexcuadron-dpo-roleplay_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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service alexcuadron-dpo-roleplay-v1-profiler
Waiting for inference service alexcuadron-dpo-roleplay-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4515.67s
Shutdown handler de-registered
alexcuadron-dpo-roleplay_v1 status is now inactive due to auto deactivation removed underperforming models
alexcuadron-dpo-roleplay_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1