developer_uid: AlexCuadron
submission_id: alexcuadron-chai-v2-sft_14944_v2
model_name: alexcuadron-chai-v2-sft_14944_v2
model_group: AlexCuadron/chai-v2-sft-
status: torndown
timestamp: 2025-03-23T14:17:01+00:00
num_battles: 10682
num_wins: 5000
celo_rating: 1258.95
family_friendly_score: 0.6113999999999999
family_friendly_standard_error: 0.006893330689876991
submission_type: basic
model_repo: AlexCuadron/chai-v2-sft-12k-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': 0.6104697294100127, 'latency_mean': 1.63798277258873, 'latency_p50': 1.6400436162948608, 'latency_p90': 1.8020777463912965}, {'batch_size': 3, 'throughput': 1.12642625719956, 'latency_mean': 2.6570151901245116, 'latency_p50': 2.6425859928131104, 'latency_p90': 2.947038173675537}, {'batch_size': 5, 'throughput': 1.3549265010171452, 'latency_mean': 3.6825984680652617, 'latency_p50': 3.689725637435913, 'latency_p90': 4.117203617095947}, {'batch_size': 6, 'throughput': 1.428317813265664, 'latency_mean': 4.180367406606674, 'latency_p50': 4.166609406471252, 'latency_p90': 4.737116813659668}, {'batch_size': 8, 'throughput': 1.4968651094653256, 'latency_mean': 5.2990196776390075, 'latency_p50': 5.289654612541199, 'latency_p90': 6.017352032661438}, {'batch_size': 10, 'throughput': 1.5453418328391741, 'latency_mean': 6.419146445989608, 'latency_p50': 6.3278738260269165, 'latency_p90': 7.387922382354736}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: alexcuadron-chai-v2-sft_14944_v2
is_internal_developer: False
language_model: AlexCuadron/chai-v2-sft-12k-12b
model_size: 13B
ranking_group: single
throughput_3p7s: 1.36
us_pacific_date: 2025-03-23
win_ratio: 0.46807713911252574
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'], '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-v2-sft-14944-v2-mkmlizer
Waiting for job on alexcuadron-chai-v2-sft-14944-v2-mkmlizer to finish
alexcuadron-chai-v2-sft-14944-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexcuadron-chai-v2-sft-14944-v2-mkmlizer: ║     _____            __           __                                ║
alexcuadron-chai-v2-sft-14944-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
alexcuadron-chai-v2-sft-14944-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
alexcuadron-chai-v2-sft-14944-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
alexcuadron-chai-v2-sft-14944-v2-mkmlizer: ║       /___/                                                         ║
alexcuadron-chai-v2-sft-14944-v2-mkmlizer: ║                                                                     ║
alexcuadron-chai-v2-sft-14944-v2-mkmlizer: ║  Version: 0.12.8                                                    ║
alexcuadron-chai-v2-sft-14944-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
alexcuadron-chai-v2-sft-14944-v2-mkmlizer: ║  https://mk1.ai                                                     ║
alexcuadron-chai-v2-sft-14944-v2-mkmlizer: ║                                                                     ║
alexcuadron-chai-v2-sft-14944-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
alexcuadron-chai-v2-sft-14944-v2-mkmlizer: ║  belonging to:                                                      ║
alexcuadron-chai-v2-sft-14944-v2-mkmlizer: ║                                                                     ║
alexcuadron-chai-v2-sft-14944-v2-mkmlizer: ║  Chai Research Corp.                                                ║
alexcuadron-chai-v2-sft-14944-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
alexcuadron-chai-v2-sft-14944-v2-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
alexcuadron-chai-v2-sft-14944-v2-mkmlizer: ║                                                                     ║
alexcuadron-chai-v2-sft-14944-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alexcuadron-chai-v2-sft-14944-v2-mkmlizer: Downloaded to shared memory in 42.876s
alexcuadron-chai-v2-sft-14944-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp53wxsofp, device:0
alexcuadron-chai-v2-sft-14944-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alexcuadron-chai-v2-sft-14944-v2-mkmlizer: quantized model in 36.910s
alexcuadron-chai-v2-sft-14944-v2-mkmlizer: Processed model AlexCuadron/chai-v2-sft-12k-12b in 79.787s
alexcuadron-chai-v2-sft-14944-v2-mkmlizer: creating bucket guanaco-mkml-models
alexcuadron-chai-v2-sft-14944-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexcuadron-chai-v2-sft-14944-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexcuadron-chai-v2-sft-14944-v2
alexcuadron-chai-v2-sft-14944-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alexcuadron-chai-v2-sft-14944-v2/config.json
alexcuadron-chai-v2-sft-14944-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alexcuadron-chai-v2-sft-14944-v2/special_tokens_map.json
alexcuadron-chai-v2-sft-14944-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexcuadron-chai-v2-sft-14944-v2/tokenizer_config.json
alexcuadron-chai-v2-sft-14944-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexcuadron-chai-v2-sft-14944-v2/tokenizer.json
alexcuadron-chai-v2-sft-14944-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 28.71it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:07, 45.42it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:07, 43.50it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:08, 41.16it/s]
Loading 0:   7%|▋         | 27/363 [00:00<00:07, 42.49it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 34.54it/s]
Loading 0:  11%|█         | 39/363 [00:00<00:07, 42.56it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:07, 42.34it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:07, 42.98it/s]
Loading 0:  15%|█▍        | 54/363 [00:01<00:07, 44.05it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:07, 40.75it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:10, 28.06it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:08, 33.67it/s]
Loading 0:  21%|██        | 76/363 [00:02<00:08, 33.13it/s]
Loading 0:  22%|██▏       | 80/363 [00:02<00:08, 33.24it/s]
Loading 0:  23%|██▎       | 84/363 [00:02<00:08, 31.06it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:07, 34.89it/s]
Loading 0:  26%|██▌       | 93/363 [00:02<00:07, 34.49it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:07, 37.41it/s]
Loading 0:  28%|██▊       | 102/363 [00:02<00:07, 36.03it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:07, 36.44it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:06, 40.20it/s]
Loading 0:  32%|███▏      | 117/363 [00:03<00:06, 38.49it/s]
Loading 0:  33%|███▎      | 121/363 [00:03<00:06, 37.65it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:06, 38.13it/s]
Loading 0:  36%|███▌      | 129/363 [00:03<00:06, 36.52it/s]
Loading 0:  37%|███▋      | 134/363 [00:03<00:05, 38.72it/s]
Loading 0:  38%|███▊      | 138/363 [00:03<00:06, 36.66it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:08, 27.10it/s]
Loading 0:  40%|████      | 146/363 [00:04<00:07, 28.77it/s]
Loading 0:  41%|████▏     | 150/363 [00:04<00:07, 28.27it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:06, 33.63it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:06, 33.49it/s]
Loading 0:  45%|████▌     | 165/363 [00:04<00:05, 36.54it/s]
Loading 0:  47%|████▋     | 169/363 [00:04<00:05, 35.28it/s]
Loading 0:  48%|████▊     | 174/363 [00:04<00:04, 38.07it/s]
Loading 0:  49%|████▉     | 178/363 [00:04<00:05, 36.64it/s]
Loading 0:  50%|█████     | 183/363 [00:05<00:04, 38.85it/s]
Loading 0:  52%|█████▏    | 187/363 [00:05<00:04, 37.01it/s]
Loading 0:  53%|█████▎    | 192/363 [00:05<00:04, 39.83it/s]
Loading 0:  54%|█████▍    | 197/363 [00:05<00:04, 40.16it/s]
Loading 0:  56%|█████▌    | 202/363 [00:05<00:03, 41.36it/s]
Loading 0:  57%|█████▋    | 207/363 [00:05<00:03, 41.80it/s]
Loading 0:  58%|█████▊    | 212/363 [00:05<00:04, 32.03it/s]
Loading 0:  60%|██████    | 218/363 [00:05<00:03, 36.88it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:04, 29.48it/s]
Loading 0:  63%|██████▎   | 227/363 [00:06<00:04, 30.53it/s]
Loading 0:  64%|██████▎   | 231/363 [00:06<00:04, 29.78it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 34.42it/s]
Loading 0:  66%|██████▋   | 241/363 [00:06<00:03, 33.80it/s]
Loading 0:  68%|██████▊   | 246/363 [00:06<00:03, 37.08it/s]
Loading 0:  69%|██████▉   | 250/363 [00:06<00:03, 35.80it/s]
Loading 0:  70%|███████   | 255/363 [00:07<00:02, 37.70it/s]
Loading 0:  71%|███████▏  | 259/363 [00:07<00:02, 35.85it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 37.80it/s]
Loading 0:  74%|███████▍  | 268/363 [00:07<00:02, 36.27it/s]
Loading 0:  75%|███████▌  | 273/363 [00:07<00:02, 38.26it/s]
Loading 0:  76%|███████▋  | 277/363 [00:07<00:02, 35.81it/s]
Loading 0:  78%|███████▊  | 282/363 [00:07<00:02, 39.30it/s]
Loading 0:  79%|███████▉  | 287/363 [00:07<00:01, 40.97it/s]
Loading 0:  80%|████████  | 292/363 [00:08<00:01, 42.49it/s]
Loading 0:  82%|████████▏ | 298/363 [00:08<00:01, 41.01it/s]
Loading 0:  84%|████████▎ | 304/363 [00:14<00:22,  2.57it/s]
Loading 0:  85%|████████▍ | 307/363 [00:15<00:18,  3.10it/s]
Loading 0:  86%|████████▌ | 312/363 [00:15<00:11,  4.33it/s]
Loading 0:  88%|████████▊ | 319/363 [00:15<00:06,  6.79it/s]
Loading 0:  89%|████████▉ | 324/363 [00:15<00:04,  8.88it/s]
Loading 0:  91%|█████████ | 329/363 [00:15<00:02, 11.56it/s]
Loading 0:  92%|█████████▏| 334/363 [00:15<00:01, 14.79it/s]
Loading 0:  93%|█████████▎| 339/363 [00:15<00:01, 16.80it/s]
Loading 0:  95%|█████████▌| 346/363 [00:15<00:00, 23.20it/s]
Loading 0:  97%|█████████▋| 351/363 [00:16<00:00, 26.68it/s]
Loading 0:  98%|█████████▊| 356/363 [00:16<00:00, 30.49it/s]
Loading 0: 100%|█████████▉| 362/363 [00:16<00:00, 33.62it/s]
                                                            

Job alexcuadron-chai-v2-sft-14944-v2-mkmlizer completed after 114.87s with status: succeeded
Stopping job with name alexcuadron-chai-v2-sft-14944-v2-mkmlizer
Pipeline stage MKMLizer completed in 115.38s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service alexcuadron-chai-v2-sft-14944-v2
Waiting for inference service alexcuadron-chai-v2-sft-14944-v2 to be ready
Inference service alexcuadron-chai-v2-sft-14944-v2 ready after 90.41010975837708s
Pipeline stage MKMLDeployer completed in 90.99s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4915356636047363s
Received healthy response to inference request in 1.598473310470581s
Received healthy response to inference request in 1.4982388019561768s
Received healthy response to inference request in 1.586193561553955s
Received healthy response to inference request in 6.482215642929077s
5 requests
0 failed requests
5th percentile: 1.5158297538757324
10th percentile: 1.533420705795288
20th percentile: 1.5686026096343995
30th percentile: 1.5886495113372803
40th percentile: 1.5935614109039307
50th percentile: 1.598473310470581
60th percentile: 1.9556982517242432
70th percentile: 2.3129231929779053
80th percentile: 3.2896716594696054
90th percentile: 4.885943651199341
95th percentile: 5.684079647064208
99th percentile: 6.3225884437561035
mean time: 2.731331396102905
Pipeline stage StressChecker completed in 14.92s
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 0.63s
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 0.71s
Shutdown handler de-registered
alexcuadron-chai-v2-sft_14944_v2 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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service alexcuadron-chai-v2-sft-14944-v2-profiler
Waiting for inference service alexcuadron-chai-v2-sft-14944-v2-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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2489.79s
Shutdown handler de-registered
alexcuadron-chai-v2-sft_14944_v2 status is now inactive due to auto deactivation removed underperforming models
alexcuadron-chai-v2-sft_14944_v2 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1