developer_uid: AlexCuadron
submission_id: alexcuadron-chai-sft-12b_v6
model_name: alexcuadron-chai-sft-12b_v5
model_group: AlexCuadron/chai-sft-12b
status: torndown
timestamp: 2025-03-13T02:33:29+00:00
num_battles: 8037
num_wins: 3712
celo_rating: 1252.01
family_friendly_score: 0.6036
family_friendly_standard_error: 0.006917615774238983
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': 0.6030939186028095, 'latency_mean': 1.6580504167079926, 'latency_p50': 1.6599637269973755, 'latency_p90': 1.8276760816574096}, {'batch_size': 3, 'throughput': 1.1138747342390314, 'latency_mean': 2.6870705485343933, 'latency_p50': 2.7077763080596924, 'latency_p90': 2.987931180000305}, {'batch_size': 5, 'throughput': 1.3442483839176773, 'latency_mean': 3.698798118829727, 'latency_p50': 3.701034188270569, 'latency_p90': 4.167309427261352}, {'batch_size': 6, 'throughput': 1.4206088899748575, 'latency_mean': 4.199329395294189, 'latency_p50': 4.1997798681259155, 'latency_p90': 4.6806196689605715}, {'batch_size': 8, 'throughput': 1.4668941407198464, 'latency_mean': 5.405050169229508, 'latency_p50': 5.435668587684631, 'latency_p90': 6.08676130771637}, {'batch_size': 10, 'throughput': 1.5080952453411864, 'latency_mean': 6.566901907920838, 'latency_p50': 6.646387338638306, 'latency_p90': 7.403988838195801}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: alexcuadron-chai-sft-12b_v5
is_internal_developer: False
language_model: AlexCuadron/chai-sft-12b
model_size: 13B
ranking_group: single
throughput_3p7s: 1.35
us_pacific_date: 2025-03-12
win_ratio: 0.46186387955704866
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-v6-mkmlizer
Waiting for job on alexcuadron-chai-sft-12b-v6-mkmlizer to finish
alexcuadron-chai-sft-12b-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexcuadron-chai-sft-12b-v6-mkmlizer: ║ _____ __ __ ║
alexcuadron-chai-sft-12b-v6-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
alexcuadron-chai-sft-12b-v6-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
alexcuadron-chai-sft-12b-v6-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
alexcuadron-chai-sft-12b-v6-mkmlizer: ║ /___/ ║
alexcuadron-chai-sft-12b-v6-mkmlizer: ║ ║
alexcuadron-chai-sft-12b-v6-mkmlizer: ║ Version: 0.12.8 ║
alexcuadron-chai-sft-12b-v6-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
alexcuadron-chai-sft-12b-v6-mkmlizer: ║ https://mk1.ai ║
alexcuadron-chai-sft-12b-v6-mkmlizer: ║ ║
alexcuadron-chai-sft-12b-v6-mkmlizer: ║ The license key for the current software has been verified as ║
alexcuadron-chai-sft-12b-v6-mkmlizer: ║ belonging to: ║
alexcuadron-chai-sft-12b-v6-mkmlizer: ║ ║
alexcuadron-chai-sft-12b-v6-mkmlizer: ║ Chai Research Corp. ║
alexcuadron-chai-sft-12b-v6-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
alexcuadron-chai-sft-12b-v6-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
alexcuadron-chai-sft-12b-v6-mkmlizer: ║ ║
alexcuadron-chai-sft-12b-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alexcuadron-chai-sft-12b-v6-mkmlizer: Downloaded to shared memory in 43.820s
alexcuadron-chai-sft-12b-v6-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpo2mexrl_, device:0
alexcuadron-chai-sft-12b-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alexcuadron-chai-sft-12b-v6-mkmlizer: quantized model in 35.675s
alexcuadron-chai-sft-12b-v6-mkmlizer: Processed model AlexCuadron/chai-sft-12b in 79.495s
alexcuadron-chai-sft-12b-v6-mkmlizer: creating bucket guanaco-mkml-models
alexcuadron-chai-sft-12b-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexcuadron-chai-sft-12b-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexcuadron-chai-sft-12b-v6
alexcuadron-chai-sft-12b-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alexcuadron-chai-sft-12b-v6/config.json
alexcuadron-chai-sft-12b-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alexcuadron-chai-sft-12b-v6/special_tokens_map.json
alexcuadron-chai-sft-12b-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexcuadron-chai-sft-12b-v6/tokenizer_config.json
alexcuadron-chai-sft-12b-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexcuadron-chai-sft-12b-v6/tokenizer.json
alexcuadron-chai-sft-12b-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alexcuadron-chai-sft-12b-v6/flywheel_model.0.safetensors
alexcuadron-chai-sft-12b-v6-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:11, 32.02it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:06, 53.59it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 48.95it/s] Loading 0: 7%|▋ | 25/363 [00:00<00:07, 47.32it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 50.27it/s] Loading 0: 10%|█ | 37/363 [00:00<00:06, 48.11it/s] Loading 0: 12%|█▏ | 42/363 [00:00<00:06, 46.99it/s] Loading 0: 13%|█▎ | 49/363 [00:00<00:05, 52.70it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 49.98it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:07, 38.46it/s] Loading 0: 18%|█▊ | 66/363 [00:01<00:07, 38.20it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:06, 42.22it/s] Loading 0: 21%|██ | 77/363 [00:01<00:06, 43.33it/s] Loading 0: 23%|██▎ | 82/363 [00:01<00:07, 36.29it/s] Loading 0: 25%|██▍ | 89/363 [00:02<00:06, 43.39it/s] Loading 0: 26%|██▌ | 94/363 [00:02<00:06, 43.08it/s] Loading 0: 27%|██▋ | 99/363 [00:02<00:06, 43.89it/s] Loading 0: 29%|██▉ | 105/363 [00:02<00:06, 42.59it/s] Loading 0: 31%|███ | 112/363 [00:02<00:05, 45.72it/s] Loading 0: 32%|███▏ | 117/363 [00:02<00:05, 43.92it/s] Loading 0: 34%|███▍ | 123/363 [00:02<00:05, 42.58it/s] Loading 0: 35%|███▌ | 128/363 [00:02<00:05, 41.96it/s] Loading 0: 37%|███▋ | 134/363 [00:03<00:04, 45.87it/s] Loading 0: 38%|███▊ | 139/363 [00:03<00:04, 45.57it/s] Loading 0: 40%|███▉ | 144/363 [00:03<00:07, 28.95it/s] Loading 0: 41%|████ | 149/363 [00:03<00:06, 30.91it/s] Loading 0: 43%|████▎ | 156/363 [00:03<00:05, 38.64it/s] Loading 0: 44%|████▍ | 161/363 [00:03<00:04, 40.42it/s] Loading 0: 46%|████▌ | 166/363 [00:03<00:04, 41.72it/s] Loading 0: 47%|████▋ | 172/363 [00:04<00:04, 41.39it/s] Loading 0: 49%|████▉ | 177/363 [00:04<00:04, 41.17it/s] Loading 0: 51%|█████ | 184/363 [00:04<00:03, 46.40it/s] Loading 0: 52%|█████▏ | 190/363 [00:04<00:03, 44.14it/s] Loading 0: 54%|█████▎ | 195/363 [00:04<00:03, 42.96it/s] Loading 0: 56%|█████▌ | 202/363 [00:04<00:03, 47.66it/s] Loading 0: 57%|█████▋ | 208/363 [00:04<00:03, 45.30it/s] Loading 0: 59%|█████▊ | 213/363 [00:04<00:03, 43.57it/s] Loading 0: 61%|██████ | 220/363 [00:05<00:02, 49.37it/s] Loading 0: 62%|██████▏ | 226/363 [00:05<00:04, 33.49it/s] Loading 0: 64%|██████▎ | 231/363 [00:05<00:03, 34.41it/s] Loading 0: 65%|██████▌ | 237/363 [00:05<00:03, 39.53it/s] Loading 0: 67%|██████▋ | 242/363 [00:05<00:02, 41.17it/s] Loading 0: 68%|██████▊ | 247/363 [00:05<00:02, 41.58it/s] Loading 0: 69%|██████▉ | 252/363 [00:05<00:02, 43.66it/s] Loading 0: 71%|███████ | 257/363 [00:06<00:02, 37.99it/s] Loading 0: 73%|███████▎ | 264/363 [00:06<00:02, 44.98it/s] Loading 0: 74%|███████▍ | 269/363 [00:06<00:02, 45.03it/s] Loading 0: 75%|███████▌ | 274/363 [00:06<00:01, 44.68it/s] Loading 0: 77%|███████▋ | 280/363 [00:06<00:01, 43.96it/s] Loading 0: 79%|███████▊ | 285/363 [00:06<00:01, 43.00it/s] Loading 0: 80%|████████ | 292/363 [00:06<00:01, 47.63it/s] Loading 0: 82%|████████▏ | 298/363 [00:06<00:01, 45.37it/s] Loading 0: 84%|████████▎ | 304/363 [00:13<00:21, 2.80it/s] Loading 0: 85%|████████▍ | 308/363 [00:13<00:15, 3.52it/s] Loading 0: 86%|████████▌ | 312/363 [00:13<00:11, 4.51it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:05, 7.34it/s] Loading 0: 90%|████████▉ | 326/363 [00:14<00:03, 9.83it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:02, 12.42it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:01, 17.33it/s] Loading 0: 95%|█████████▍| 344/363 [00:14<00:00, 21.10it/s] Loading 0: 96%|█████████▌| 349/363 [00:14<00:00, 24.42it/s] Loading 0: 98%|█████████▊| 356/363 [00:14<00:00, 31.13it/s] Loading 0: 100%|█████████▉| 362/363 [00:14<00:00, 34.17it/s]
Job alexcuadron-chai-sft-12b-v6-mkmlizer completed after 104.23s with status: succeeded
Stopping job with name alexcuadron-chai-sft-12b-v6-mkmlizer
Pipeline stage MKMLizer completed in 104.75s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service alexcuadron-chai-sft-12b-v6
Waiting for inference service alexcuadron-chai-sft-12b-v6 to be ready
Inference service alexcuadron-chai-sft-12b-v6 ready after 100.3627667427063s
Pipeline stage MKMLDeployer completed in 100.92s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4572064876556396s
Received healthy response to inference request in 1.4311046600341797s
Received healthy response to inference request in 1.3999321460723877s
Received healthy response to inference request in 1.4601776599884033s
Received healthy response to inference request in 1.4862425327301025s
5 requests
0 failed requests
5th percentile: 1.4061666488647462
10th percentile: 1.4124011516571044
20th percentile: 1.4248701572418212
30th percentile: 1.4369192600250245
40th percentile: 1.4485484600067138
50th percentile: 1.4601776599884033
60th percentile: 1.470603609085083
70th percentile: 1.4810295581817627
80th percentile: 1.68043532371521
90th percentile: 2.068820905685425
95th percentile: 2.263013696670532
99th percentile: 2.418367929458618
mean time: 1.6469326972961427
Pipeline stage StressChecker completed in 9.51s
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 0.81s
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 0.65s
Shutdown handler de-registered
alexcuadron-chai-sft-12b_v6 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 2654.01s
Shutdown handler de-registered
alexcuadron-chai-sft-12b_v6 status is now inactive due to auto deactivation removed underperforming models
alexcuadron-chai-sft-12b_v6 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1