developer_uid: AlexCuadron
submission_id: alexcuadron-chai-sft-12b_v4
model_name: alexcuadron-chai-sft-12b_v4
model_group: AlexCuadron/chai-sft-12b
status: torndown
timestamp: 2025-03-13T01:11:16+00:00
num_battles: 7553
num_wins: 3427
celo_rating: 1245.13
family_friendly_score: 0.597
family_friendly_standard_error: 0.006936728335461898
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': 0.6010126562823339, 'latency_mean': 1.663791744709015, 'latency_p50': 1.67183518409729, 'latency_p90': 1.8352548599243164}, {'batch_size': 3, 'throughput': 1.0902780477750427, 'latency_mean': 2.7419296169281004, 'latency_p50': 2.755824327468872, 'latency_p90': 3.020484137535095}, {'batch_size': 5, 'throughput': 1.3226231078538218, 'latency_mean': 3.7569679737091066, 'latency_p50': 3.745672106742859, 'latency_p90': 4.216584157943726}, {'batch_size': 6, 'throughput': 1.399615736221468, 'latency_mean': 4.269590058326721, 'latency_p50': 4.243614077568054, 'latency_p90': 4.796656322479248}, {'batch_size': 8, 'throughput': 1.4474798553551322, 'latency_mean': 5.48711329460144, 'latency_p50': 5.518117308616638, 'latency_p90': 6.243227648735046}, {'batch_size': 10, 'throughput': 1.4830310828139777, 'latency_mean': 6.691877648830414, 'latency_p50': 6.703330755233765, 'latency_p90': 7.522836327552795}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: alexcuadron-chai-sft-12b_v4
is_internal_developer: False
language_model: AlexCuadron/chai-sft-12b
model_size: 13B
ranking_group: single
throughput_3p7s: 1.32
us_pacific_date: 2025-03-12
win_ratio: 0.4537269958956706
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-v4-mkmlizer
Waiting for job on alexcuadron-chai-sft-12b-v4-mkmlizer to finish
alexcuadron-chai-sft-12b-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexcuadron-chai-sft-12b-v4-mkmlizer: ║     _____            __           __                                ║
alexcuadron-chai-sft-12b-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
alexcuadron-chai-sft-12b-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
alexcuadron-chai-sft-12b-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
alexcuadron-chai-sft-12b-v4-mkmlizer: ║       /___/                                                         ║
alexcuadron-chai-sft-12b-v4-mkmlizer: ║                                                                     ║
alexcuadron-chai-sft-12b-v4-mkmlizer: ║  Version: 0.12.8                                                    ║
alexcuadron-chai-sft-12b-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
alexcuadron-chai-sft-12b-v4-mkmlizer: ║  https://mk1.ai                                                     ║
alexcuadron-chai-sft-12b-v4-mkmlizer: ║                                                                     ║
alexcuadron-chai-sft-12b-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
alexcuadron-chai-sft-12b-v4-mkmlizer: ║  belonging to:                                                      ║
alexcuadron-chai-sft-12b-v4-mkmlizer: ║                                                                     ║
alexcuadron-chai-sft-12b-v4-mkmlizer: ║  Chai Research Corp.                                                ║
alexcuadron-chai-sft-12b-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
alexcuadron-chai-sft-12b-v4-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
alexcuadron-chai-sft-12b-v4-mkmlizer: ║                                                                     ║
alexcuadron-chai-sft-12b-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alexcuadron-chai-sft-12b-v4-mkmlizer: Downloaded to shared memory in 51.114s
alexcuadron-chai-sft-12b-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpq62osy5o, device:0
alexcuadron-chai-sft-12b-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission jellywibble-enzo-mafia-enemy_v12: HTTPConnectionPool(host='jellywibble-enzo-mafia-enemy-v12-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
alexcuadron-chai-sft-12b-v4-mkmlizer: quantized model in 37.395s
alexcuadron-chai-sft-12b-v4-mkmlizer: Processed model AlexCuadron/chai-sft-12b in 88.510s
alexcuadron-chai-sft-12b-v4-mkmlizer: creating bucket guanaco-mkml-models
alexcuadron-chai-sft-12b-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexcuadron-chai-sft-12b-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexcuadron-chai-sft-12b-v4
alexcuadron-chai-sft-12b-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alexcuadron-chai-sft-12b-v4/config.json
alexcuadron-chai-sft-12b-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alexcuadron-chai-sft-12b-v4/special_tokens_map.json
alexcuadron-chai-sft-12b-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexcuadron-chai-sft-12b-v4/tokenizer_config.json
alexcuadron-chai-sft-12b-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexcuadron-chai-sft-12b-v4/tokenizer.json
alexcuadron-chai-sft-12b-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alexcuadron-chai-sft-12b-v4/flywheel_model.0.safetensors
alexcuadron-chai-sft-12b-v4-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 29.31it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 49.43it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 47.36it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 45.87it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 52.03it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 49.57it/s]
Loading 0:  12%|█▏        | 43/363 [00:00<00:06, 48.66it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 50.19it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 45.72it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 34.36it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 33.20it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 39.44it/s]
Loading 0:  21%|██        | 77/363 [00:01<00:06, 41.14it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:08, 34.41it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:06, 41.69it/s]
Loading 0:  26%|██▌       | 94/363 [00:02<00:06, 41.87it/s]
Loading 0:  27%|██▋       | 99/363 [00:02<00:06, 42.90it/s]
Loading 0:  29%|██▉       | 105/363 [00:02<00:06, 41.51it/s]
Loading 0:  31%|███       | 112/363 [00:02<00:05, 45.70it/s]
Loading 0:  32%|███▏      | 117/363 [00:02<00:05, 42.30it/s]
Loading 0:  34%|███▎      | 122/363 [00:02<00:05, 44.15it/s]
Loading 0:  35%|███▍      | 127/363 [00:03<00:06, 37.86it/s]
Loading 0:  37%|███▋      | 134/363 [00:03<00:05, 44.00it/s]
Loading 0:  38%|███▊      | 139/363 [00:03<00:05, 41.70it/s]
Loading 0:  40%|███▉      | 144/363 [00:03<00:07, 27.84it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:07, 29.24it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 35.65it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 36.05it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 37.42it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:05, 38.39it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 31.78it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 38.45it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:04, 38.55it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:04, 38.48it/s]
Loading 0:  55%|█████▍    | 198/363 [00:04<00:04, 39.69it/s]
Loading 0:  56%|█████▌    | 203/363 [00:05<00:04, 33.70it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 40.38it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 39.02it/s]
Loading 0:  61%|██████    | 220/363 [00:05<00:03, 40.03it/s]
Loading 0:  62%|██████▏   | 225/363 [00:05<00:05, 24.69it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:04, 26.71it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 33.24it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 34.09it/s]
Loading 0:  68%|██████▊   | 246/363 [00:06<00:03, 34.64it/s]
Loading 0:  69%|██████▉   | 250/363 [00:06<00:03, 33.25it/s]
Loading 0:  70%|███████   | 255/363 [00:06<00:03, 34.77it/s]
Loading 0:  71%|███████▏  | 259/363 [00:06<00:03, 32.99it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 34.60it/s]
Loading 0:  74%|███████▍  | 268/363 [00:07<00:02, 33.66it/s]
Loading 0:  75%|███████▌  | 273/363 [00:07<00:02, 35.90it/s]
Loading 0:  76%|███████▋  | 277/363 [00:07<00:02, 34.34it/s]
Loading 0:  78%|███████▊  | 282/363 [00:07<00:02, 36.98it/s]
Loading 0:  79%|███████▉  | 286/363 [00:07<00:02, 34.69it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 37.03it/s]
Loading 0:  81%|████████▏ | 295/363 [00:07<00:01, 35.32it/s]
Loading 0:  82%|████████▏ | 299/363 [00:08<00:01, 34.54it/s]
Loading 0:  84%|████████▎ | 304/363 [00:14<00:28,  2.09it/s]
Loading 0:  85%|████████▍ | 307/363 [00:15<00:21,  2.62it/s]
Loading 0:  86%|████████▌ | 312/363 [00:15<00:13,  3.88it/s]
Loading 0:  88%|████████▊ | 320/363 [00:15<00:06,  6.66it/s]
Loading 0:  90%|████████▉ | 326/363 [00:15<00:04,  9.13it/s]
Loading 0:  91%|█████████ | 331/363 [00:15<00:02, 11.64it/s]
Loading 0:  93%|█████████▎| 338/363 [00:15<00:01, 16.44it/s]
Loading 0:  95%|█████████▍| 344/363 [00:15<00:00, 20.10it/s]
Loading 0:  96%|█████████▌| 349/363 [00:15<00:00, 23.20it/s]
Loading 0:  98%|█████████▊| 356/363 [00:16<00:00, 29.55it/s]
Loading 0: 100%|█████████▉| 362/363 [00:16<00:00, 31.88it/s]
                                                            

Job alexcuadron-chai-sft-12b-v4-mkmlizer completed after 114.05s with status: succeeded
Stopping job with name alexcuadron-chai-sft-12b-v4-mkmlizer
Pipeline stage MKMLizer completed in 114.54s
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-v4
Waiting for inference service alexcuadron-chai-sft-12b-v4 to be ready
Failed to get response for submission jellywibble-enzo-mafia-enemy_v12: HTTPConnectionPool(host='jellywibble-enzo-mafia-enemy-v12-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service alexcuadron-chai-sft-12b-v4 ready after 100.35500407218933s
Pipeline stage MKMLDeployer completed in 100.86s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3865067958831787s
Received healthy response to inference request in 1.5420572757720947s
Received healthy response to inference request in 1.5795767307281494s
Received healthy response to inference request in 1.4187099933624268s
Received healthy response to inference request in 1.2912890911102295s
5 requests
0 failed requests
5th percentile: 1.316773271560669
10th percentile: 1.3422574520111084
20th percentile: 1.3932258129119872
30th percentile: 1.4433794498443604
40th percentile: 1.4927183628082275
50th percentile: 1.5420572757720947
60th percentile: 1.5570650577545166
70th percentile: 1.5720728397369386
80th percentile: 1.7409627437591555
90th percentile: 2.063734769821167
95th percentile: 2.225120782852173
99th percentile: 2.3542295932769775
mean time: 1.643627977371216
Pipeline stage StressChecker completed in 9.55s
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 0.73s
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 0.77s
Shutdown handler de-registered
alexcuadron-chai-sft-12b_v4 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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service alexcuadron-chai-sft-12b-v4-profiler
Waiting for inference service alexcuadron-chai-sft-12b-v4-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 4408.01s
Shutdown handler de-registered
alexcuadron-chai-sft-12b_v4 status is now inactive due to auto deactivation removed underperforming models
alexcuadron-chai-sft-12b_v4 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1