developer_uid: AlexCuadron
submission_id: alexcuadron-chai-c3-dpo-rica_v1
model_name: alexcuadron-chai-c3-dpo-rica_v1
model_group: AlexCuadron/chai-c3_dpo_
status: torndown
timestamp: 2025-03-13T10:38:25+00:00
num_battles: 10073
num_wins: 4614
celo_rating: 1253.8
family_friendly_score: 0.6084
family_friendly_standard_error: 0.006902889829629328
submission_type: basic
model_repo: AlexCuadron/chai-c3_dpo_rica
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6020092908921125, 'latency_mean': 1.6610410165786744, 'latency_p50': 1.6530576944351196, 'latency_p90': 1.835175061225891}, {'batch_size': 3, 'throughput': 1.0986415830903267, 'latency_mean': 2.7177423775196075, 'latency_p50': 2.7403876781463623, 'latency_p90': 2.970336675643921}, {'batch_size': 5, 'throughput': 1.3173767768977065, 'latency_mean': 3.773305379152298, 'latency_p50': 3.777316451072693, 'latency_p90': 4.225859880447388}, {'batch_size': 6, 'throughput': 1.4011792290161542, 'latency_mean': 4.255952587127686, 'latency_p50': 4.267845630645752, 'latency_p90': 4.695411539077758}, {'batch_size': 8, 'throughput': 1.4608535896995483, 'latency_mean': 5.448594237565994, 'latency_p50': 5.488725543022156, 'latency_p90': 6.171983122825623}, {'batch_size': 10, 'throughput': 1.5068250139230652, 'latency_mean': 6.576205539703369, 'latency_p50': 6.557429552078247, 'latency_p90': 7.438004040718079}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: alexcuadron-chai-c3-dpo-rica_v1
is_internal_developer: False
language_model: AlexCuadron/chai-c3_dpo_rica
model_size: 13B
ranking_group: single
throughput_3p7s: 1.31
us_pacific_date: 2025-03-13
win_ratio: 0.4580561898143552
generation_params: {'temperature': 0.95, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', 'User:', 'Me:', '####', 'You:', 'Bot:', '</s>'], '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-chai-c3-dpo-rica-v1-mkmlizer
Waiting for job on alexcuadron-chai-c3-dpo-rica-v1-mkmlizer to finish
alexcuadron-chai-c3-dpo-rica-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexcuadron-chai-c3-dpo-rica-v1-mkmlizer: ║ _____ __ __ ║
alexcuadron-chai-c3-dpo-rica-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
alexcuadron-chai-c3-dpo-rica-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
alexcuadron-chai-c3-dpo-rica-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
alexcuadron-chai-c3-dpo-rica-v1-mkmlizer: ║ /___/ ║
alexcuadron-chai-c3-dpo-rica-v1-mkmlizer: ║ ║
alexcuadron-chai-c3-dpo-rica-v1-mkmlizer: ║ Version: 0.12.8 ║
alexcuadron-chai-c3-dpo-rica-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
alexcuadron-chai-c3-dpo-rica-v1-mkmlizer: ║ https://mk1.ai ║
alexcuadron-chai-c3-dpo-rica-v1-mkmlizer: ║ ║
alexcuadron-chai-c3-dpo-rica-v1-mkmlizer: ║ The license key for the current software has been verified as ║
alexcuadron-chai-c3-dpo-rica-v1-mkmlizer: ║ belonging to: ║
alexcuadron-chai-c3-dpo-rica-v1-mkmlizer: ║ ║
alexcuadron-chai-c3-dpo-rica-v1-mkmlizer: ║ Chai Research Corp. ║
alexcuadron-chai-c3-dpo-rica-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
alexcuadron-chai-c3-dpo-rica-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
alexcuadron-chai-c3-dpo-rica-v1-mkmlizer: ║ ║
alexcuadron-chai-c3-dpo-rica-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alexcuadron-chai-c3-dpo-rica-v1-mkmlizer: Downloaded to shared memory in 40.637s
alexcuadron-chai-c3-dpo-rica-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpeyhmelat, device:0
alexcuadron-chai-c3-dpo-rica-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alexcuadron-chai-c3-dpo-rica-v1-mkmlizer: quantized model in 35.127s
alexcuadron-chai-c3-dpo-rica-v1-mkmlizer: Processed model AlexCuadron/chai-c3_dpo_rica in 75.765s
alexcuadron-chai-c3-dpo-rica-v1-mkmlizer: creating bucket guanaco-mkml-models
alexcuadron-chai-c3-dpo-rica-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexcuadron-chai-c3-dpo-rica-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexcuadron-chai-c3-dpo-rica-v1
alexcuadron-chai-c3-dpo-rica-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alexcuadron-chai-c3-dpo-rica-v1/config.json
alexcuadron-chai-c3-dpo-rica-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alexcuadron-chai-c3-dpo-rica-v1/special_tokens_map.json
alexcuadron-chai-c3-dpo-rica-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexcuadron-chai-c3-dpo-rica-v1/tokenizer_config.json
alexcuadron-chai-c3-dpo-rica-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexcuadron-chai-c3-dpo-rica-v1/tokenizer.json
alexcuadron-chai-c3-dpo-rica-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alexcuadron-chai-c3-dpo-rica-v1/flywheel_model.0.safetensors
alexcuadron-chai-c3-dpo-rica-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:11, 31.98it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:06, 54.05it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:06, 51.01it/s] Loading 0: 7%|▋ | 25/363 [00:00<00:06, 52.14it/s] Loading 0: 9%|▉ | 32/363 [00:00<00:06, 47.99it/s] Loading 0: 11%|█ | 40/363 [00:00<00:05, 56.51it/s] Loading 0: 13%|█▎ | 46/363 [00:00<00:05, 53.54it/s] Loading 0: 14%|█▍ | 52/363 [00:00<00:05, 53.86it/s] Loading 0: 17%|█▋ | 60/363 [00:01<00:05, 55.07it/s] Loading 0: 18%|█▊ | 66/363 [00:01<00:07, 37.59it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:06, 41.87it/s] Loading 0: 21%|██▏ | 78/363 [00:01<00:06, 42.42it/s] Loading 0: 23%|██▎ | 83/363 [00:01<00:06, 43.15it/s] Loading 0: 25%|██▍ | 90/363 [00:01<00:05, 47.71it/s] Loading 0: 26%|██▋ | 96/363 [00:02<00:05, 45.06it/s] Loading 0: 28%|██▊ | 101/363 [00:02<00:05, 44.10it/s] Loading 0: 30%|███ | 109/363 [00:02<00:04, 52.16it/s] Loading 0: 32%|███▏ | 115/363 [00:02<00:05, 47.87it/s] Loading 0: 33%|███▎ | 121/363 [00:02<00:05, 46.81it/s] Loading 0: 35%|███▍ | 127/363 [00:02<00:05, 43.12it/s] Loading 0: 37%|███▋ | 135/363 [00:02<00:04, 49.45it/s] Loading 0: 39%|███▉ | 141/363 [00:02<00:04, 47.29it/s] Loading 0: 40%|████ | 146/363 [00:03<00:06, 34.72it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 34.57it/s] Loading 0: 43%|████▎ | 156/363 [00:03<00:05, 39.80it/s] Loading 0: 44%|████▍ | 161/363 [00:03<00:04, 41.28it/s] Loading 0: 46%|████▌ | 167/363 [00:03<00:04, 39.56it/s] Loading 0: 48%|████▊ | 175/363 [00:03<00:03, 47.05it/s] Loading 0: 50%|████▉ | 181/363 [00:04<00:04, 45.26it/s] Loading 0: 51%|█████ | 186/363 [00:04<00:03, 44.98it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 49.44it/s] Loading 0: 55%|█████▍ | 199/363 [00:04<00:03, 47.76it/s] Loading 0: 56%|█████▌ | 204/363 [00:04<00:03, 43.18it/s] Loading 0: 58%|█████▊ | 210/363 [00:04<00:03, 46.92it/s] Loading 0: 59%|█████▉ | 215/363 [00:04<00:03, 47.08it/s] Loading 0: 61%|██████ | 222/363 [00:04<00:02, 47.17it/s] Loading 0: 63%|██████▎ | 227/363 [00:05<00:04, 33.09it/s] Loading 0: 64%|██████▎ | 231/363 [00:05<00:03, 33.13it/s] Loading 0: 65%|██████▌ | 237/363 [00:05<00:03, 38.36it/s] Loading 0: 67%|██████▋ | 242/363 [00:05<00:03, 40.32it/s] Loading 0: 68%|██████▊ | 247/363 [00:05<00:02, 42.45it/s] Loading 0: 70%|██████▉ | 253/363 [00:05<00:02, 42.49it/s] Loading 0: 71%|███████ | 258/363 [00:05<00:02, 42.10it/s] Loading 0: 73%|███████▎ | 264/363 [00:05<00:02, 46.04it/s] Loading 0: 74%|███████▍ | 269/363 [00:06<00:02, 45.25it/s] Loading 0: 75%|███████▌ | 274/363 [00:06<00:01, 45.42it/s] Loading 0: 77%|███████▋ | 280/363 [00:06<00:01, 43.74it/s] Loading 0: 79%|███████▊ | 285/363 [00:06<00:01, 42.26it/s] Loading 0: 80%|████████ | 291/363 [00:06<00:01, 46.25it/s] Loading 0: 82%|████████▏ | 296/363 [00:06<00:01, 45.86it/s] Loading 0: 83%|████████▎ | 303/363 [00:06<00:01, 44.64it/s] Loading 0: 85%|████████▍ | 308/363 [00:13<00:20, 2.64it/s] Loading 0: 86%|████████▌ | 312/363 [00:13<00:15, 3.36it/s] Loading 0: 88%|████████▊ | 320/363 [00:13<00:07, 5.45it/s] Loading 0: 90%|████████▉ | 326/363 [00:13<00:04, 7.40it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:03, 9.48it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:01, 13.46it/s] Loading 0: 95%|█████████▍| 344/363 [00:14<00:01, 16.65it/s] Loading 0: 96%|█████████▌| 349/363 [00:14<00:00, 19.69it/s] Loading 0: 98%|█████████▊| 356/363 [00:14<00:00, 26.01it/s] Loading 0: 100%|█████████▉| 362/363 [00:14<00:00, 29.26it/s]
Job alexcuadron-chai-c3-dpo-rica-v1-mkmlizer completed after 104.36s with status: succeeded
Stopping job with name alexcuadron-chai-c3-dpo-rica-v1-mkmlizer
Pipeline stage MKMLizer completed in 104.83s
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-chai-c3-dpo-rica-v1
Waiting for inference service alexcuadron-chai-c3-dpo-rica-v1 to be ready
Inference service alexcuadron-chai-c3-dpo-rica-v1 ready after 100.43495059013367s
Pipeline stage MKMLDeployer completed in 100.97s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.125823497772217s
Received healthy response to inference request in 1.5530376434326172s
Received healthy response to inference request in 1.9525659084320068s
Received healthy response to inference request in 1.4658074378967285s
Received healthy response to inference request in 1.4722955226898193s
5 requests
0 failed requests
5th percentile: 1.4671050548553466
10th percentile: 1.4684026718139649
20th percentile: 1.4709979057312013
30th percentile: 1.488443946838379
40th percentile: 1.520740795135498
50th percentile: 1.5530376434326172
60th percentile: 1.712848949432373
70th percentile: 1.8726602554321288
80th percentile: 1.9872174263000488
90th percentile: 2.056520462036133
95th percentile: 2.091171979904175
99th percentile: 2.118893194198608
mean time: 1.7139060020446777
Pipeline stage StressChecker completed in 9.96s
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 0.71s
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 0.86s
Shutdown handler de-registered
alexcuadron-chai-c3-dpo-rica_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 4286.01s
Shutdown handler de-registered
alexcuadron-chai-c3-dpo-rica_v1 status is now inactive due to auto deactivation removed underperforming models
alexcuadron-chai-c3-dpo-rica_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1