developer_uid: chai_backend_admin
submission_id: chaiml-caesar-russian-m_98477_v1
model_name: chaiml-caesar-russian-m_98477_v1
model_group: ChaiML/Caesar-Russian-ma
status: torndown
timestamp: 2025-05-08T21:11:08+00:00
num_battles: 7701
num_wins: 4241
celo_rating: 1306.74
family_friendly_score: 0.5444
family_friendly_standard_error: 0.0070431333935969155
submission_type: basic
model_repo: ChaiML/Caesar-Russian-mafia_richard-mafia-bos250508084501_sft
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.5373533610879716, 'latency_mean': 1.860918585062027, 'latency_p50': 1.8321986198425293, 'latency_p90': 2.0987759113311766}, {'batch_size': 3, 'throughput': 1.0870433370912613, 'latency_mean': 2.747140909433365, 'latency_p50': 2.725257635116577, 'latency_p90': 3.071021842956543}, {'batch_size': 5, 'throughput': 1.392253645262647, 'latency_mean': 3.5730020713806154, 'latency_p50': 3.580264925956726, 'latency_p90': 3.9279863357543947}, {'batch_size': 6, 'throughput': 1.4974487735769502, 'latency_mean': 3.971286579370499, 'latency_p50': 4.015301823616028, 'latency_p90': 4.427475380897522}, {'batch_size': 8, 'throughput': 1.661543825679242, 'latency_mean': 4.771703684329987, 'latency_p50': 4.757311820983887, 'latency_p90': 5.362707471847534}, {'batch_size': 10, 'throughput': 1.75479464818977, 'latency_mean': 5.648965662717819, 'latency_p50': 5.615366458892822, 'latency_p90': 6.376467204093933}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: chaiml-caesar-russian-m_98477_v1
is_internal_developer: True
language_model: ChaiML/Caesar-Russian-mafia_richard-mafia-bos250508084501_sft
model_size: 24B
ranking_group: single
throughput_3p7s: 1.44
us_pacific_date: 2025-05-08
win_ratio: 0.5507077002986626
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', 'You:', '####\n', '</s>', '####'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}</s>\n', 'user_template': 'You: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': True}
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 chaiml-caesar-russian-m-98477-v1-mkmlizer
Waiting for job on chaiml-caesar-russian-m-98477-v1-mkmlizer to finish
chaiml-caesar-russian-m-98477-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-caesar-russian-m-98477-v1-mkmlizer: ║ _____ __ __ ║
chaiml-caesar-russian-m-98477-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-caesar-russian-m-98477-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-caesar-russian-m-98477-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-caesar-russian-m-98477-v1-mkmlizer: ║ /___/ ║
chaiml-caesar-russian-m-98477-v1-mkmlizer: ║ ║
chaiml-caesar-russian-m-98477-v1-mkmlizer: ║ Version: 0.12.8 ║
chaiml-caesar-russian-m-98477-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-caesar-russian-m-98477-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-caesar-russian-m-98477-v1-mkmlizer: ║ ║
chaiml-caesar-russian-m-98477-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-caesar-russian-m-98477-v1-mkmlizer: ║ belonging to: ║
chaiml-caesar-russian-m-98477-v1-mkmlizer: ║ ║
chaiml-caesar-russian-m-98477-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-caesar-russian-m-98477-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-caesar-russian-m-98477-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-caesar-russian-m-98477-v1-mkmlizer: ║ ║
chaiml-caesar-russian-m-98477-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-caesar-russian-m-98477-v1-mkmlizer: Downloaded to shared memory in 77.762s
chaiml-caesar-russian-m-98477-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp4jybh4si, device:0
chaiml-caesar-russian-m-98477-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-caesar-russian-m-98477-v1-mkmlizer: quantized model in 52.370s
chaiml-caesar-russian-m-98477-v1-mkmlizer: Processed model ChaiML/Caesar-Russian-mafia_richard-mafia-bos250508084501_sft in 130.132s
chaiml-caesar-russian-m-98477-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-caesar-russian-m-98477-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-caesar-russian-m-98477-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-caesar-russian-m-98477-v1
chaiml-caesar-russian-m-98477-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-caesar-russian-m-98477-v1/config.json
chaiml-caesar-russian-m-98477-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-caesar-russian-m-98477-v1/special_tokens_map.json
chaiml-caesar-russian-m-98477-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-caesar-russian-m-98477-v1/tokenizer_config.json
chaiml-caesar-russian-m-98477-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-caesar-russian-m-98477-v1/tokenizer.json
chaiml-caesar-russian-m-98477-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-caesar-russian-m-98477-v1/flywheel_model.1.safetensors
chaiml-caesar-russian-m-98477-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-caesar-russian-m-98477-v1/flywheel_model.0.safetensors
chaiml-caesar-russian-m-98477-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:16, 21.71it/s] Loading 0: 3%|▎ | 12/363 [00:00<00:09, 37.94it/s] Loading 0: 5%|▍ | 17/363 [00:00<00:09, 35.09it/s] Loading 0: 6%|▌ | 21/363 [00:00<00:09, 35.67it/s] Loading 0: 7%|▋ | 25/363 [00:00<00:10, 32.00it/s] Loading 0: 9%|▉ | 32/363 [00:00<00:08, 37.56it/s] Loading 0: 10%|▉ | 36/363 [00:01<00:14, 22.70it/s] Loading 0: 11%|█ | 40/363 [00:01<00:12, 25.51it/s] Loading 0: 12%|█▏ | 44/363 [00:01<00:12, 26.29it/s] Loading 0: 13%|█▎ | 48/363 [00:01<00:11, 27.35it/s] Loading 0: 14%|█▍ | 52/363 [00:01<00:11, 26.01it/s] Loading 0: 16%|█▌ | 57/363 [00:01<00:10, 28.60it/s] Loading 0: 17%|█▋ | 61/363 [00:02<00:11, 26.87it/s] Loading 0: 18%|█▊ | 65/363 [00:02<00:10, 27.93it/s] Loading 0: 19%|█▉ | 70/363 [00:02<00:11, 24.98it/s] Loading 0: 20%|██ | 73/363 [00:02<00:13, 21.76it/s] Loading 0: 22%|██▏ | 79/363 [00:02<00:10, 27.05it/s] Loading 0: 23%|██▎ | 82/363 [00:02<00:10, 25.89it/s] Loading 0: 24%|██▎ | 86/363 [00:03<00:10, 27.50it/s] Loading 0: 25%|██▍ | 89/363 [00:03<00:10, 27.22it/s] Loading 0: 25%|██▌ | 92/363 [00:03<00:12, 21.82it/s] Loading 0: 27%|██▋ | 99/363 [00:03<00:09, 29.04it/s] Loading 0: 28%|██▊ | 103/363 [00:03<00:09, 28.00it/s] Loading 0: 29%|██▉ | 107/363 [00:03<00:10, 23.81it/s] Loading 0: 31%|███ | 112/363 [00:04<00:09, 26.89it/s] Loading 0: 32%|███▏ | 115/363 [00:04<00:09, 26.82it/s] Loading 0: 33%|███▎ | 120/363 [00:04<00:08, 29.51it/s] Loading 0: 34%|███▍ | 124/363 [00:04<00:08, 27.66it/s] Loading 0: 36%|███▌ | 129/363 [00:04<00:07, 30.01it/s] Loading 0: 37%|███▋ | 133/363 [00:04<00:08, 28.33it/s] Loading 0: 38%|███▊ | 138/363 [00:04<00:07, 30.67it/s] Loading 0: 39%|███▉ | 142/363 [00:05<00:07, 29.10it/s] Loading 0: 41%|████ | 148/363 [00:05<00:06, 35.64it/s] Loading 0: 42%|████▏ | 152/363 [00:05<00:08, 24.61it/s] Loading 0: 43%|████▎ | 156/363 [00:05<00:08, 24.19it/s] Loading 0: 44%|████▍ | 159/363 [00:05<00:08, 23.17it/s] Loading 0: 45%|████▌ | 165/363 [00:06<00:07, 27.80it/s] Loading 0: 47%|████▋ | 169/363 [00:06<00:07, 27.02it/s] Loading 0: 48%|████▊ | 174/363 [00:06<00:06, 29.72it/s] Loading 0: 49%|████▉ | 178/363 [00:06<00:06, 28.58it/s] Loading 0: 50%|█████ | 182/363 [00:06<00:06, 28.68it/s] Loading 0: 52%|█████▏ | 187/363 [00:06<00:06, 26.40it/s] Loading 0: 52%|█████▏ | 190/363 [00:06<00:07, 24.31it/s] Loading 0: 53%|█████▎ | 193/363 [00:07<00:06, 25.12it/s] Loading 0: 54%|█████▍ | 196/363 [00:07<00:06, 25.19it/s] Loading 0: 55%|█████▌ | 200/363 [00:21<00:06, 25.19it/s] Loading 0: 55%|█████▌ | 201/363 [00:21<02:54, 1.08s/it] Loading 0: 56%|█████▌ | 203/363 [00:21<02:24, 1.11it/s] Loading 0: 57%|█████▋ | 208/363 [00:21<01:26, 1.79it/s] Loading 0: 58%|█████▊ | 211/363 [00:21<01:06, 2.27it/s] Loading 0: 59%|█████▉ | 214/363 [00:21<00:49, 2.99it/s] Loading 0: 60%|██████ | 218/363 [00:21<00:33, 4.27it/s] Loading 0: 61%|██████ | 221/363 [00:21<00:26, 5.44it/s] Loading 0: 62%|██████▏ | 224/363 [00:22<00:21, 6.53it/s] Loading 0: 63%|██████▎ | 229/363 [00:22<00:13, 9.62it/s] Loading 0: 64%|██████▍ | 232/363 [00:22<00:11, 11.42it/s] Loading 0: 65%|██████▌ | 237/363 [00:22<00:08, 15.40it/s] Loading 0: 66%|██████▌ | 240/363 [00:22<00:07, 15.93it/s] Loading 0: 67%|██████▋ | 244/363 [00:22<00:06, 19.38it/s] Loading 0: 68%|██████▊ | 247/363 [00:22<00:05, 21.18it/s] Loading 0: 69%|██████▉ | 250/363 [00:23<00:05, 21.89it/s] Loading 0: 70%|███████ | 255/363 [00:23<00:04, 25.18it/s] Loading 0: 71%|███████ | 258/363 [00:23<00:04, 23.34it/s] Loading 0: 72%|███████▏ | 262/363 [00:23<00:03, 26.82it/s] Loading 0: 74%|███████▎ | 267/363 [00:23<00:03, 24.46it/s] Loading 0: 74%|███████▍ | 270/363 [00:23<00:04, 20.57it/s] Loading 0: 75%|███████▌ | 274/363 [00:24<00:03, 23.95it/s] Loading 0: 76%|███████▋ | 277/363 [00:24<00:03, 23.92it/s] Loading 0: 78%|███████▊ | 282/363 [00:24<00:03, 26.44it/s] Loading 0: 79%|███████▊ | 285/363 [00:24<00:03, 24.35it/s] Loading 0: 80%|████████ | 291/363 [00:24<00:02, 29.54it/s] Loading 0: 81%|████████▏ | 295/363 [00:24<00:02, 28.15it/s] Loading 0: 82%|████████▏ | 299/363 [00:24<00:02, 28.15it/s] Loading 0: 84%|████████▎ | 304/363 [00:25<00:02, 25.94it/s] Loading 0: 85%|████████▍ | 307/363 [00:25<00:02, 24.20it/s] Loading 0: 85%|████████▌ | 310/363 [00:25<00:02, 25.07it/s] Loading 0: 86%|████████▌ | 313/363 [00:25<00:01, 25.70it/s] Loading 0: 88%|████████▊ | 318/363 [00:25<00:01, 28.84it/s] Loading 0: 88%|████████▊ | 321/363 [00:25<00:01, 26.13it/s] Loading 0: 90%|█████████ | 327/363 [00:25<00:01, 31.31it/s] Loading 0: 91%|█████████ | 331/363 [00:26<00:01, 29.95it/s] Loading 0: 92%|█████████▏| 335/363 [00:26<00:00, 29.79it/s] Loading 0: 93%|█████████▎| 339/363 [00:26<00:00, 29.80it/s] Loading 0: 94%|█████████▍| 342/363 [00:33<00:11, 1.81it/s] Loading 0: 96%|█████████▌| 347/363 [00:33<00:05, 2.77it/s] Loading 0: 96%|█████████▋| 350/363 [00:33<00:03, 3.51it/s] Loading 0: 98%|█████████▊| 355/363 [00:33<00:01, 5.27it/s] Loading 0: 99%|█████████▉| 359/363 [00:33<00:00, 6.86it/s]
Job chaiml-caesar-russian-m-98477-v1-mkmlizer completed after 155.92s with status: succeeded
Stopping job with name chaiml-caesar-russian-m-98477-v1-mkmlizer
Pipeline stage MKMLizer completed in 156.43s
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 chaiml-caesar-russian-m-98477-v1
Waiting for inference service chaiml-caesar-russian-m-98477-v1 to be ready
Inference service chaiml-caesar-russian-m-98477-v1 ready after 140.52792096138s
Pipeline stage MKMLDeployer completed in 141.04s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4042413234710693s
Received healthy response to inference request in 2.102363348007202s
Received healthy response to inference request in 2.1021649837493896s
Received healthy response to inference request in 1.797513484954834s
Received healthy response to inference request in 2.2529666423797607s
5 requests
0 failed requests
5th percentile: 1.8584437847137452
10th percentile: 1.9193740844726563
20th percentile: 2.0412346839904787
30th percentile: 2.1022046566009522
40th percentile: 2.102284002304077
50th percentile: 2.102363348007202
60th percentile: 2.1626046657562257
70th percentile: 2.222845983505249
80th percentile: 2.2832215785980225
90th percentile: 2.3437314510345457
95th percentile: 2.3739863872528075
99th percentile: 2.398190336227417
mean time: 2.1318499565124513
Pipeline stage StressChecker completed in 11.80s
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 0.65s
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 0.61s
Shutdown handler de-registered
chaiml-caesar-russian-m_98477_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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2828.72s
Shutdown handler de-registered
chaiml-caesar-russian-m_98477_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-caesar-russian-m_98477_v1 status is now torndown due to DeploymentManager action