developer_uid: AlexCuadron
submission_id: alexcuadron-chai-sft-12b_v1
model_name: alexcuadron-chai-sft-12b_v1
model_group: AlexCuadron/chai-sft-12b
status: torndown
timestamp: 2025-03-12T10:11:23+00:00
num_battles: 10450
num_wins: 4058
celo_rating: 1202.21
family_friendly_score: 0.655
family_friendly_standard_error: 0.006722722662731224
submission_type: basic
model_repo: AlexCuadron/chai-sft-12b
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6089997808275142, 'latency_mean': 1.641939002275467, 'latency_p50': 1.6399644613265991, 'latency_p90': 1.8323662519454955}, {'batch_size': 3, 'throughput': 1.118014034937139, 'latency_mean': 2.676203339099884, 'latency_p50': 2.6873373985290527, 'latency_p90': 2.907888150215149}, {'batch_size': 5, 'throughput': 1.36158568176652, 'latency_mean': 3.661817808151245, 'latency_p50': 3.6545932292938232, 'latency_p90': 4.1247259140014645}, {'batch_size': 6, 'throughput': 1.4247544281335927, 'latency_mean': 4.186787326335907, 'latency_p50': 4.1920576095581055, 'latency_p90': 4.730070614814759}, {'batch_size': 8, 'throughput': 1.4827289925782048, 'latency_mean': 5.377095079421997, 'latency_p50': 5.399502515792847, 'latency_p90': 6.1538026332855225}, {'batch_size': 10, 'throughput': 1.5300257313873877, 'latency_mean': 6.508877277374268, 'latency_p50': 6.486324667930603, 'latency_p90': 7.353009033203125}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: alexcuadron-chai-sft-12b_v1
is_internal_developer: False
language_model: AlexCuadron/chai-sft-12b
model_size: 13B
ranking_group: single
throughput_3p7s: 1.37
us_pacific_date: 2025-03-12
win_ratio: 0.38832535885167463
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, '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-chai-sft-12b-v1-mkmlizer
Waiting for job on alexcuadron-chai-sft-12b-v1-mkmlizer to finish
alexcuadron-chai-sft-12b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexcuadron-chai-sft-12b-v1-mkmlizer: ║ _____ __ __ ║
alexcuadron-chai-sft-12b-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
alexcuadron-chai-sft-12b-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
alexcuadron-chai-sft-12b-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
alexcuadron-chai-sft-12b-v1-mkmlizer: ║ /___/ ║
alexcuadron-chai-sft-12b-v1-mkmlizer: ║ ║
alexcuadron-chai-sft-12b-v1-mkmlizer: ║ Version: 0.12.8 ║
alexcuadron-chai-sft-12b-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
alexcuadron-chai-sft-12b-v1-mkmlizer: ║ https://mk1.ai ║
alexcuadron-chai-sft-12b-v1-mkmlizer: ║ ║
alexcuadron-chai-sft-12b-v1-mkmlizer: ║ The license key for the current software has been verified as ║
alexcuadron-chai-sft-12b-v1-mkmlizer: ║ belonging to: ║
alexcuadron-chai-sft-12b-v1-mkmlizer: ║ ║
alexcuadron-chai-sft-12b-v1-mkmlizer: ║ Chai Research Corp. ║
alexcuadron-chai-sft-12b-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
alexcuadron-chai-sft-12b-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
alexcuadron-chai-sft-12b-v1-mkmlizer: ║ ║
alexcuadron-chai-sft-12b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alexcuadron-chai-sft-12b-v1-mkmlizer: Downloaded to shared memory in 41.462s
alexcuadron-chai-sft-12b-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpg1v17y5g, device:0
alexcuadron-chai-sft-12b-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alexcuadron-chai-sft-12b-v1-mkmlizer: quantized model in 35.777s
alexcuadron-chai-sft-12b-v1-mkmlizer: Processed model AlexCuadron/chai-sft-12b in 77.240s
alexcuadron-chai-sft-12b-v1-mkmlizer: creating bucket guanaco-mkml-models
alexcuadron-chai-sft-12b-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexcuadron-chai-sft-12b-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexcuadron-chai-sft-12b-v1
alexcuadron-chai-sft-12b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alexcuadron-chai-sft-12b-v1/config.json
alexcuadron-chai-sft-12b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alexcuadron-chai-sft-12b-v1/special_tokens_map.json
alexcuadron-chai-sft-12b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexcuadron-chai-sft-12b-v1/tokenizer_config.json
alexcuadron-chai-sft-12b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexcuadron-chai-sft-12b-v1/tokenizer.json
alexcuadron-chai-sft-12b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alexcuadron-chai-sft-12b-v1/flywheel_model.0.safetensors
alexcuadron-chai-sft-12b-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:11, 31.55it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:06, 52.39it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 47.32it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:07, 46.33it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 52.37it/s] Loading 0: 10%|█ | 37/363 [00:00<00:06, 47.63it/s] Loading 0: 12%|█▏ | 42/363 [00:00<00:07, 45.75it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:06, 50.85it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 47.58it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:08, 35.33it/s] Loading 0: 18%|█▊ | 66/363 [00:01<00:08, 35.67it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 39.78it/s] Loading 0: 21%|██ | 77/363 [00:01<00:06, 41.84it/s] Loading 0: 23%|██▎ | 82/363 [00:01<00:07, 36.30it/s] Loading 0: 25%|██▍ | 90/363 [00:02<00:06, 44.17it/s] Loading 0: 26%|██▋ | 96/363 [00:02<00:06, 42.60it/s] Loading 0: 28%|██▊ | 101/363 [00:02<00:06, 40.88it/s] Loading 0: 30%|██▉ | 108/363 [00:02<00:05, 47.37it/s] Loading 0: 31%|███▏ | 114/363 [00:02<00:05, 42.74it/s] Loading 0: 33%|███▎ | 119/363 [00:02<00:06, 40.62it/s] Loading 0: 35%|███▍ | 126/363 [00:02<00:05, 45.26it/s] Loading 0: 36%|███▋ | 132/363 [00:03<00:05, 44.32it/s] Loading 0: 38%|███▊ | 137/363 [00:03<00:05, 43.52it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:06, 33.89it/s] Loading 0: 40%|████ | 146/363 [00:03<00:06, 34.34it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 32.62it/s] Loading 0: 43%|████▎ | 156/363 [00:03<00:05, 38.36it/s] Loading 0: 44%|████▍ | 161/363 [00:03<00:05, 39.27it/s] Loading 0: 46%|████▌ | 166/363 [00:03<00:04, 40.53it/s] Loading 0: 47%|████▋ | 171/363 [00:04<00:04, 42.56it/s] Loading 0: 48%|████▊ | 176/363 [00:04<00:05, 36.80it/s] Loading 0: 50%|█████ | 183/363 [00:04<00:04, 44.47it/s] Loading 0: 52%|█████▏ | 188/363 [00:04<00:03, 45.11it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 44.84it/s] Loading 0: 55%|█████▍ | 199/363 [00:04<00:03, 43.50it/s] Loading 0: 56%|█████▌ | 204/363 [00:04<00:03, 42.77it/s] Loading 0: 58%|█████▊ | 210/363 [00:04<00:03, 46.39it/s] Loading 0: 59%|█████▉ | 215/363 [00:05<00:03, 46.19it/s] Loading 0: 61%|██████ | 222/363 [00:05<00:03, 46.54it/s] Loading 0: 63%|██████▎ | 227/363 [00:05<00:04, 33.04it/s] Loading 0: 64%|██████▎ | 231/363 [00:05<00:04, 31.65it/s] Loading 0: 65%|██████▌ | 237/363 [00:05<00:03, 37.55it/s] Loading 0: 67%|██████▋ | 242/363 [00:05<00:03, 39.85it/s] Loading 0: 68%|██████▊ | 247/363 [00:05<00:02, 41.10it/s] Loading 0: 69%|██████▉ | 252/363 [00:06<00:02, 42.76it/s] Loading 0: 71%|███████ | 257/363 [00:06<00:02, 37.93it/s] Loading 0: 73%|███████▎ | 265/363 [00:06<00:02, 46.19it/s] Loading 0: 75%|███████▍ | 271/363 [00:06<00:02, 44.39it/s] Loading 0: 76%|███████▌ | 276/363 [00:06<00:02, 43.29it/s] Loading 0: 78%|███████▊ | 282/363 [00:06<00:01, 46.75it/s] Loading 0: 79%|███████▉ | 287/363 [00:06<00:01, 47.06it/s] Loading 0: 80%|████████ | 292/363 [00:06<00:01, 46.71it/s] Loading 0: 82%|████████▏ | 298/363 [00:07<00:01, 45.02it/s] Loading 0: 84%|████████▎ | 304/363 [00:13<00:22, 2.68it/s] Loading 0: 85%|████████▍ | 308/363 [00:14<00:16, 3.39it/s] Loading 0: 86%|████████▌ | 312/363 [00:14<00:11, 4.37it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:05, 7.18it/s] Loading 0: 90%|████████▉ | 326/363 [00:14<00:03, 9.70it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:02, 12.26it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:01, 17.12it/s] Loading 0: 95%|█████████▍| 344/363 [00:14<00:00, 21.04it/s] Loading 0: 96%|█████████▌| 349/363 [00:14<00:00, 24.11it/s] Loading 0: 98%|█████████▊| 356/363 [00:14<00:00, 30.87it/s] Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 34.11it/s]
Job alexcuadron-chai-sft-12b-v1-mkmlizer completed after 104.15s with status: succeeded
Stopping job with name alexcuadron-chai-sft-12b-v1-mkmlizer
Pipeline stage MKMLizer completed in 104.62s
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-sft-12b-v1
Waiting for inference service alexcuadron-chai-sft-12b-v1 to be ready
Inference service alexcuadron-chai-sft-12b-v1 ready after 90.34193181991577s
Pipeline stage MKMLDeployer completed in 90.84s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0985608100891113s
Received healthy response to inference request in 1.4624912738800049s
Received healthy response to inference request in 1.5554108619689941s
Received healthy response to inference request in 1.5386171340942383s
Received healthy response to inference request in 1.4466075897216797s
5 requests
0 failed requests
5th percentile: 1.4497843265533448
10th percentile: 1.4529610633850099
20th percentile: 1.4593145370483398
30th percentile: 1.4777164459228516
40th percentile: 1.508166790008545
50th percentile: 1.5386171340942383
60th percentile: 1.5453346252441407
70th percentile: 1.552052116394043
80th percentile: 1.6640408515930176
90th percentile: 1.8813008308410646
95th percentile: 1.9899308204650878
99th percentile: 2.0768348121643068
mean time: 1.6203375339508057
Pipeline stage StressChecker completed in 9.34s
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 0.68s
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 0.68s
Shutdown handler de-registered
alexcuadron-chai-sft-12b_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 4369.14s
Shutdown handler de-registered
alexcuadron-chai-sft-12b_v1 status is now inactive due to auto deactivation removed underperforming models
alexcuadron-chai-sft-12b_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1