developer_uid: AlexCuadron
submission_id: alexcuadron-dpo-roleplay-v3_v1
model_name: alexcuadron-dpo-roleplay-v3_v1
model_group: AlexCuadron/dpo_roleplay
status: torndown
timestamp: 2025-03-24T20:03:57+00:00
num_battles: 7727
num_wins: 3758
celo_rating: 1267.07
family_friendly_score: 0.5896
family_friendly_standard_error: 0.0069566060690540756
submission_type: basic
model_repo: AlexCuadron/dpo_roleplay_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': 0.6177260399922995, 'latency_mean': 1.6187790942192077, 'latency_p50': 1.5935289859771729, 'latency_p90': 1.8036663055419921}, {'batch_size': 3, 'throughput': 1.1217609401046824, 'latency_mean': 2.6695758688449858, 'latency_p50': 2.6521600484848022, 'latency_p90': 2.9349026918411254}, {'batch_size': 5, 'throughput': 1.3482226802982693, 'latency_mean': 3.6837239706516267, 'latency_p50': 3.682913064956665, 'latency_p90': 4.132314229011536}, {'batch_size': 6, 'throughput': 1.423560514980323, 'latency_mean': 4.194089652299881, 'latency_p50': 4.20748770236969, 'latency_p90': 4.661862778663635}, {'batch_size': 8, 'throughput': 1.4749405335053472, 'latency_mean': 5.379328520298004, 'latency_p50': 5.419646978378296, 'latency_p90': 5.988247632980347}, {'batch_size': 10, 'throughput': 1.518318717039392, 'latency_mean': 6.535429505109787, 'latency_p50': 6.579349040985107, 'latency_p90': 7.262262439727783}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: alexcuadron-dpo-roleplay-v3_v1
is_internal_developer: False
language_model: AlexCuadron/dpo_roleplay_v3
model_size: 13B
ranking_group: single
throughput_3p7s: 1.36
us_pacific_date: 2025-03-24
win_ratio: 0.4863465769380096
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}\n<START>\n', '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-v3-v1-mkmlizer
Waiting for job on alexcuadron-dpo-roleplay-v3-v1-mkmlizer to finish
alexcuadron-dpo-roleplay-v3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexcuadron-dpo-roleplay-v3-v1-mkmlizer: ║ _____ __ __ ║
alexcuadron-dpo-roleplay-v3-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
alexcuadron-dpo-roleplay-v3-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
alexcuadron-dpo-roleplay-v3-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
alexcuadron-dpo-roleplay-v3-v1-mkmlizer: ║ /___/ ║
alexcuadron-dpo-roleplay-v3-v1-mkmlizer: ║ ║
alexcuadron-dpo-roleplay-v3-v1-mkmlizer: ║ Version: 0.12.8 ║
alexcuadron-dpo-roleplay-v3-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
alexcuadron-dpo-roleplay-v3-v1-mkmlizer: ║ https://mk1.ai ║
alexcuadron-dpo-roleplay-v3-v1-mkmlizer: ║ ║
alexcuadron-dpo-roleplay-v3-v1-mkmlizer: ║ The license key for the current software has been verified as ║
alexcuadron-dpo-roleplay-v3-v1-mkmlizer: ║ belonging to: ║
alexcuadron-dpo-roleplay-v3-v1-mkmlizer: ║ ║
alexcuadron-dpo-roleplay-v3-v1-mkmlizer: ║ Chai Research Corp. ║
alexcuadron-dpo-roleplay-v3-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
alexcuadron-dpo-roleplay-v3-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
alexcuadron-dpo-roleplay-v3-v1-mkmlizer: ║ ║
alexcuadron-dpo-roleplay-v3-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Retrying (%r) after connection broken by '%r': %s
alexcuadron-dpo-roleplay-v3-v1-mkmlizer: Downloaded to shared memory in 43.379s
alexcuadron-dpo-roleplay-v3-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpw2ls7k3s, device:0
alexcuadron-dpo-roleplay-v3-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alexcuadron-dpo-roleplay-v3-v1-mkmlizer: quantized model in 35.635s
alexcuadron-dpo-roleplay-v3-v1-mkmlizer: Processed model AlexCuadron/dpo_roleplay_v3 in 79.014s
alexcuadron-dpo-roleplay-v3-v1-mkmlizer: creating bucket guanaco-mkml-models
alexcuadron-dpo-roleplay-v3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexcuadron-dpo-roleplay-v3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexcuadron-dpo-roleplay-v3-v1
alexcuadron-dpo-roleplay-v3-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alexcuadron-dpo-roleplay-v3-v1/config.json
alexcuadron-dpo-roleplay-v3-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alexcuadron-dpo-roleplay-v3-v1/special_tokens_map.json
alexcuadron-dpo-roleplay-v3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexcuadron-dpo-roleplay-v3-v1/tokenizer_config.json
alexcuadron-dpo-roleplay-v3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexcuadron-dpo-roleplay-v3-v1/tokenizer.json
alexcuadron-dpo-roleplay-v3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alexcuadron-dpo-roleplay-v3-v1/flywheel_model.0.safetensors
alexcuadron-dpo-roleplay-v3-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%|▌ | 19/363 [00:06<00:59, 5.80it/s] Loading 0: 7%|▋ | 24/363 [00:06<00:41, 8.09it/s] Loading 0: 9%|▉ | 32/363 [00:06<00:24, 13.32it/s] Loading 0: 10%|█ | 38/363 [00:06<00:18, 17.18it/s] Loading 0: 12%|█▏ | 43/363 [00:07<00:18, 17.06it/s] Loading 0: 14%|█▍ | 50/363 [00:07<00:13, 22.93it/s] Loading 0: 15%|█▌ | 56/363 [00:07<00:11, 26.72it/s] Loading 0: 17%|█▋ | 61/363 [00:07<00:10, 29.86it/s] Loading 0: 19%|█▊ | 68/363 [00:07<00:08, 36.60it/s] Loading 0: 20%|██ | 74/363 [00:07<00:07, 38.66it/s] Loading 0: 22%|██▏ | 79/363 [00:07<00:07, 39.84it/s] Loading 0: 24%|██▎ | 86/363 [00:07<00:06, 45.80it/s] Loading 0: 25%|██▌ | 92/363 [00:08<00:06, 44.99it/s] Loading 0: 27%|██▋ | 97/363 [00:08<00:05, 44.47it/s] Loading 0: 29%|██▊ | 104/363 [00:08<00:05, 48.46it/s] Loading 0: 30%|███ | 110/363 [00:08<00:05, 45.17it/s] Loading 0: 32%|███▏ | 115/363 [00:08<00:05, 43.71it/s] Loading 0: 33%|███▎ | 121/363 [00:08<00:07, 34.44it/s] Loading 0: 34%|███▍ | 125/363 [00:08<00:06, 34.69it/s] Loading 0: 36%|███▌ | 131/363 [00:09<00:05, 39.33it/s] Loading 0: 38%|███▊ | 137/363 [00:09<00:05, 40.90it/s] Loading 0: 39%|███▉ | 142/363 [00:09<00:05, 41.06it/s] Loading 0: 41%|████ | 148/363 [00:09<00:04, 45.21it/s] Loading 0: 42%|████▏ | 153/363 [00:09<00:04, 46.03it/s] Loading 0: 44%|████▎ | 158/363 [00:09<00:04, 46.89it/s] Loading 0: 45%|████▌ | 164/363 [00:09<00:04, 46.02it/s] Loading 0: 47%|████▋ | 169/363 [00:09<00:04, 43.58it/s] Loading 0: 48%|████▊ | 175/363 [00:10<00:03, 47.49it/s] Loading 0: 50%|████▉ | 180/363 [00:10<00:03, 45.88it/s] Loading 0: 51%|█████ | 185/363 [00:10<00:03, 46.43it/s] Loading 0: 53%|█████▎ | 191/363 [00:10<00:03, 44.75it/s] Loading 0: 54%|█████▍ | 196/363 [00:10<00:03, 42.88it/s] Loading 0: 56%|█████▌ | 202/363 [00:10<00:04, 34.39it/s] Loading 0: 57%|█████▋ | 206/363 [00:10<00:04, 34.52it/s] Loading 0: 58%|█████▊ | 212/363 [00:11<00:03, 38.41it/s] Loading 0: 60%|██████ | 218/363 [00:11<00:03, 39.82it/s] Loading 0: 61%|██████▏ | 223/363 [00:11<00:03, 40.82it/s] Loading 0: 63%|██████▎ | 230/363 [00:11<00:02, 45.72it/s] Loading 0: 65%|██████▌ | 236/363 [00:11<00:02, 44.03it/s] Loading 0: 66%|██████▋ | 241/363 [00:11<00:02, 40.72it/s] Loading 0: 68%|██████▊ | 247/363 [00:11<00:02, 45.09it/s] Loading 0: 69%|██████▉ | 252/363 [00:11<00:02, 43.95it/s] Loading 0: 71%|███████ | 257/363 [00:12<00:02, 43.88it/s] Loading 0: 72%|███████▏ | 263/363 [00:12<00:02, 43.01it/s] Loading 0: 74%|███████▍ | 268/363 [00:12<00:02, 43.08it/s] Loading 0: 76%|███████▌ | 275/363 [00:12<00:01, 47.96it/s] Loading 0: 77%|███████▋ | 280/363 [00:12<00:01, 45.65it/s] Loading 0: 79%|███████▊ | 285/363 [00:12<00:02, 26.71it/s] Loading 0: 80%|████████ | 292/363 [00:13<00:02, 33.87it/s] Loading 0: 82%|████████▏ | 297/363 [00:13<00:01, 35.82it/s] Loading 0: 83%|████████▎ | 302/363 [00:13<00:01, 35.04it/s] Loading 0: 85%|████████▍ | 307/363 [00:13<00:01, 37.41it/s] Loading 0: 86%|████████▌ | 312/363 [00:13<00:01, 34.41it/s] Loading 0: 88%|████████▊ | 319/363 [00:13<00:01, 41.22it/s] Loading 0: 89%|████████▉ | 324/363 [00:13<00:00, 41.71it/s] Loading 0: 91%|█████████ | 329/363 [00:13<00:00, 43.38it/s] Loading 0: 92%|█████████▏| 335/363 [00:14<00:00, 43.40it/s] Loading 0: 94%|█████████▎| 340/363 [00:14<00:00, 43.43it/s] Loading 0: 95%|█████████▌| 346/363 [00:14<00:00, 47.30it/s] Loading 0: 97%|█████████▋| 351/363 [00:14<00:00, 45.22it/s] Loading 0: 98%|█████████▊| 356/363 [00:14<00:00, 46.37it/s] Loading 0: 100%|█████████▉| 362/363 [00:14<00:00, 45.65it/s]
Job alexcuadron-dpo-roleplay-v3-v1-mkmlizer completed after 104.55s with status: succeeded
Stopping job with name alexcuadron-dpo-roleplay-v3-v1-mkmlizer
Pipeline stage MKMLizer completed in 105.08s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service alexcuadron-dpo-roleplay-v3-v1
Waiting for inference service alexcuadron-dpo-roleplay-v3-v1 to be ready
Inference service alexcuadron-dpo-roleplay-v3-v1 ready after 90.3041877746582s
Pipeline stage MKMLDeployer completed in 91.03s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2592616081237793s
Received healthy response to inference request in 1.8774471282958984s
Received healthy response to inference request in 1.7764079570770264s
Received healthy response to inference request in 1.6965208053588867s
Received healthy response to inference request in 1.7500286102294922s
5 requests
0 failed requests
5th percentile: 1.7072223663330077
10th percentile: 1.717923927307129
20th percentile: 1.7393270492553712
30th percentile: 1.755304479598999
40th percentile: 1.7658562183380127
50th percentile: 1.7764079570770264
60th percentile: 1.816823625564575
70th percentile: 1.857239294052124
80th percentile: 1.9538100242614747
90th percentile: 2.106535816192627
95th percentile: 2.182898712158203
99th percentile: 2.243989028930664
mean time: 1.8719332218170166
Pipeline stage StressChecker completed in 11.03s
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 0.78s
Shutdown handler de-registered
alexcuadron-dpo-roleplay-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 2686.62s
Shutdown handler de-registered
alexcuadron-dpo-roleplay-v3_v1 status is now inactive due to auto deactivation removed underperforming models
alexcuadron-dpo-roleplay-v3_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1