developer_uid: chai_backend_admin
submission_id: chaiml-caesar-russian-m_37631_v1
model_name: chaiml-caesar-russian-m_37631_v1
model_group: ChaiML/Caesar-Russian-ma
status: torndown
timestamp: 2025-04-26T07:16:58+00:00
num_battles: 10133
num_wins: 4935
celo_rating: 1280.67
family_friendly_score: 0.49
family_friendly_standard_error: 0.007069653456853455
submission_type: basic
model_repo: ChaiML/Caesar-Russian-mafia_richard-mafia-bos250425185342_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': 0.5286409744994957, 'latency_mean': 1.891585179567337, 'latency_p50': 1.9120566844940186, 'latency_p90': 2.09021110534668}, {'batch_size': 3, 'throughput': 1.0760970419553937, 'latency_mean': 2.779380021095276, 'latency_p50': 2.777354121208191, 'latency_p90': 3.044981670379639}, {'batch_size': 5, 'throughput': 1.3832956137488517, 'latency_mean': 3.591668440103531, 'latency_p50': 3.6161303520202637, 'latency_p90': 4.011007833480835}, {'batch_size': 6, 'throughput': 1.4883775937999066, 'latency_mean': 4.007970327138901, 'latency_p50': 4.02229118347168, 'latency_p90': 4.5072335481643675}, {'batch_size': 8, 'throughput': 1.6186269480441158, 'latency_mean': 4.897282544374466, 'latency_p50': 4.966321706771851, 'latency_p90': 5.437808847427368}, {'batch_size': 10, 'throughput': 1.7378645276704237, 'latency_mean': 5.6820035636425015, 'latency_p50': 5.694355487823486, 'latency_p90': 6.417842602729797}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: chaiml-caesar-russian-m_37631_v1
is_internal_developer: True
language_model: ChaiML/Caesar-Russian-mafia_richard-mafia-bos250425185342_sft
model_size: 24B
ranking_group: single
throughput_3p7s: 1.42
us_pacific_date: 2025-04-26
win_ratio: 0.4870225994276127
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', '\n', '####', 'You:', '</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-37631-v1-mkmlizer
Waiting for job on chaiml-caesar-russian-m-37631-v1-mkmlizer to finish
chaiml-caesar-russian-m-37631-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-caesar-russian-m-37631-v1-mkmlizer: ║ _____ __ __ ║
chaiml-caesar-russian-m-37631-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-caesar-russian-m-37631-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-caesar-russian-m-37631-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-caesar-russian-m-37631-v1-mkmlizer: ║ /___/ ║
chaiml-caesar-russian-m-37631-v1-mkmlizer: ║ ║
chaiml-caesar-russian-m-37631-v1-mkmlizer: ║ Version: 0.12.8 ║
chaiml-caesar-russian-m-37631-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-caesar-russian-m-37631-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-caesar-russian-m-37631-v1-mkmlizer: ║ ║
chaiml-caesar-russian-m-37631-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-caesar-russian-m-37631-v1-mkmlizer: ║ belonging to: ║
chaiml-caesar-russian-m-37631-v1-mkmlizer: ║ ║
chaiml-caesar-russian-m-37631-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-caesar-russian-m-37631-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-caesar-russian-m-37631-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-caesar-russian-m-37631-v1-mkmlizer: ║ ║
chaiml-caesar-russian-m-37631-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-caesar-russian-m-37631-v1-mkmlizer: Downloaded to shared memory in 79.066s
chaiml-caesar-russian-m-37631-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp7lun9xea, device:0
chaiml-caesar-russian-m-37631-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-caesar-russian-m-37631-v1-mkmlizer: quantized model in 54.852s
chaiml-caesar-russian-m-37631-v1-mkmlizer: Processed model ChaiML/Caesar-Russian-mafia_richard-mafia-bos250425185342_sft in 133.918s
chaiml-caesar-russian-m-37631-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-caesar-russian-m-37631-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-caesar-russian-m-37631-v1
chaiml-caesar-russian-m-37631-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-caesar-russian-m-37631-v1/config.json
chaiml-caesar-russian-m-37631-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-caesar-russian-m-37631-v1/special_tokens_map.json
chaiml-caesar-russian-m-37631-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-caesar-russian-m-37631-v1/tokenizer_config.json
chaiml-caesar-russian-m-37631-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-caesar-russian-m-37631-v1/tokenizer.json
chaiml-caesar-russian-m-37631-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-caesar-russian-m-37631-v1/flywheel_model.1.safetensors
chaiml-caesar-russian-m-37631-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-caesar-russian-m-37631-v1/flywheel_model.0.safetensors
chaiml-caesar-russian-m-37631-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:16, 21.18it/s] Loading 0: 3%|▎ | 12/363 [00:00<00:09, 38.07it/s] Loading 0: 5%|▍ | 17/363 [00:00<00:09, 35.32it/s] Loading 0: 6%|▌ | 21/363 [00:00<00:09, 36.22it/s] Loading 0: 7%|▋ | 25/363 [00:00<00:10, 31.59it/s] Loading 0: 9%|▉ | 32/363 [00:00<00:08, 38.20it/s] Loading 0: 10%|█ | 37/363 [00:01<00:13, 24.53it/s] Loading 0: 11%|█▏ | 41/363 [00:01<00:14, 22.66it/s] Loading 0: 13%|█▎ | 48/363 [00:01<00:11, 28.64it/s] Loading 0: 14%|█▍ | 52/363 [00:01<00:11, 27.14it/s] Loading 0: 16%|█▌ | 57/363 [00:01<00:10, 30.02it/s] Loading 0: 17%|█▋ | 61/363 [00:02<00:10, 28.29it/s] Loading 0: 18%|█▊ | 65/363 [00:02<00:10, 29.17it/s] Loading 0: 19%|█▉ | 70/363 [00:02<00:11, 26.63it/s] Loading 0: 20%|██ | 73/363 [00:02<00:13, 22.22it/s] Loading 0: 22%|██▏ | 79/363 [00:02<00:10, 27.61it/s] Loading 0: 23%|██▎ | 83/363 [00:02<00:09, 28.06it/s] Loading 0: 24%|██▍ | 87/363 [00:03<00:11, 23.06it/s] Loading 0: 25%|██▌ | 91/363 [00:03<00:10, 25.15it/s] Loading 0: 26%|██▌ | 94/363 [00:03<00:10, 25.10it/s] Loading 0: 27%|██▋ | 99/363 [00:03<00:09, 27.49it/s] Loading 0: 28%|██▊ | 102/363 [00:03<00:10, 24.27it/s] Loading 0: 29%|██▉ | 107/363 [00:04<00:12, 21.20it/s] Loading 0: 31%|███ | 111/363 [00:04<00:10, 23.95it/s] Loading 0: 31%|███▏ | 114/363 [00:04<00:11, 20.81it/s] Loading 0: 33%|███▎ | 120/363 [00:04<00:09, 25.72it/s] Loading 0: 34%|███▍ | 123/363 [00:04<00:10, 22.86it/s] Loading 0: 36%|███▌ | 129/363 [00:04<00:08, 26.73it/s] Loading 0: 36%|███▋ | 132/363 [00:05<00:10, 22.75it/s] Loading 0: 38%|███▊ | 138/363 [00:05<00:08, 27.17it/s] Loading 0: 39%|███▉ | 141/363 [00:05<00:09, 24.29it/s] Loading 0: 40%|████ | 147/363 [00:05<00:06, 31.28it/s] Loading 0: 42%|████▏ | 151/363 [00:05<00:09, 21.65it/s] Loading 0: 42%|████▏ | 154/363 [00:06<00:10, 20.28it/s] Loading 0: 43%|████▎ | 157/363 [00:06<00:09, 21.35it/s] Loading 0: 44%|████▍ | 160/363 [00:06<00:09, 22.15it/s] Loading 0: 45%|████▌ | 165/363 [00:06<00:07, 25.28it/s] Loading 0: 46%|████▋ | 168/363 [00:06<00:08, 22.97it/s] Loading 0: 48%|████▊ | 174/363 [00:06<00:06, 28.25it/s] Loading 0: 49%|████▉ | 177/363 [00:06<00:07, 24.95it/s] Loading 0: 50%|█████ | 182/363 [00:07<00:06, 27.61it/s] Loading 0: 52%|█████▏ | 187/363 [00:07<00:07, 23.51it/s] Loading 0: 52%|█████▏ | 190/363 [00:07<00:08, 21.37it/s] Loading 0: 53%|█████▎ | 193/363 [00:07<00:07, 22.24it/s] Loading 0: 54%|█████▍ | 196/363 [00:07<00:07, 22.75it/s] Loading 0: 55%|█████▌ | 200/363 [00:22<00:07, 22.75it/s] Loading 0: 55%|█████▌ | 201/363 [00:22<03:03, 1.13s/it] Loading 0: 56%|█████▌ | 203/363 [00:22<02:32, 1.05it/s] Loading 0: 57%|█████▋ | 208/363 [00:22<01:31, 1.69it/s] Loading 0: 58%|█████▊ | 211/363 [00:22<01:10, 2.16it/s] Loading 0: 59%|█████▉ | 214/363 [00:23<00:52, 2.83it/s] Loading 0: 60%|██████ | 218/363 [00:23<00:35, 4.04it/s] Loading 0: 61%|██████ | 221/363 [00:23<00:27, 5.18it/s] Loading 0: 62%|██████▏ | 224/363 [00:23<00:22, 6.15it/s] Loading 0: 63%|██████▎ | 228/363 [00:23<00:15, 8.59it/s] Loading 0: 64%|██████▎ | 231/363 [00:23<00:13, 9.98it/s] Loading 0: 65%|██████▌ | 237/363 [00:23<00:08, 14.85it/s] Loading 0: 66%|██████▌ | 240/363 [00:24<00:07, 15.54it/s] Loading 0: 68%|██████▊ | 246/363 [00:24<00:05, 20.87it/s] Loading 0: 69%|██████▉ | 250/363 [00:24<00:05, 21.72it/s] Loading 0: 70%|███████ | 255/363 [00:24<00:04, 25.10it/s] Loading 0: 71%|███████▏ | 259/363 [00:24<00:04, 24.65it/s] Loading 0: 73%|███████▎ | 265/363 [00:24<00:03, 31.47it/s] Loading 0: 74%|███████▍ | 269/363 [00:25<00:04, 22.28it/s] Loading 0: 75%|███████▌ | 273/363 [00:25<00:04, 21.77it/s] Loading 0: 76%|███████▌ | 276/363 [00:25<00:04, 20.66it/s] Loading 0: 77%|███████▋ | 280/363 [00:25<00:03, 23.92it/s] Loading 0: 78%|███████▊ | 283/363 [00:25<00:03, 24.54it/s] Loading 0: 79%|███████▉ | 286/363 [00:25<00:03, 24.16it/s] Loading 0: 80%|████████ | 291/363 [00:26<00:02, 26.72it/s] Loading 0: 81%|████████ | 294/363 [00:26<00:02, 23.54it/s] Loading 0: 82%|████████▏ | 299/363 [00:26<00:02, 26.56it/s] Loading 0: 84%|████████▎ | 304/363 [00:26<00:02, 24.06it/s] Loading 0: 85%|████████▍ | 307/363 [00:26<00:02, 22.16it/s] Loading 0: 85%|████████▌ | 310/363 [00:26<00:02, 23.16it/s] Loading 0: 86%|████████▌ | 313/363 [00:26<00:02, 24.13it/s] Loading 0: 88%|████████▊ | 318/363 [00:27<00:01, 26.87it/s] Loading 0: 88%|████████▊ | 321/363 [00:27<00:01, 23.42it/s] Loading 0: 90%|█████████ | 327/363 [00:27<00:01, 27.89it/s] Loading 0: 91%|█████████ | 330/363 [00:27<00:01, 24.00it/s] Loading 0: 92%|█████████▏| 335/363 [00:27<00:01, 26.31it/s] Loading 0: 93%|█████████▎| 338/363 [00:27<00:01, 24.73it/s] Loading 0: 94%|█████████▍| 341/363 [00:34<00:13, 1.64it/s] Loading 0: 96%|█████████▌| 347/363 [00:35<00:05, 2.73it/s] Loading 0: 96%|█████████▋| 350/363 [00:35<00:03, 3.43it/s] Loading 0: 98%|█████████▊| 355/363 [00:35<00:01, 5.09it/s] Loading 0: 99%|█████████▉| 359/363 [00:35<00:00, 6.56it/s]
Job chaiml-caesar-russian-m-37631-v1-mkmlizer completed after 165.19s with status: succeeded
Stopping job with name chaiml-caesar-russian-m-37631-v1-mkmlizer
Pipeline stage MKMLizer completed in 165.68s
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 chaiml-caesar-russian-m-37631-v1
Waiting for inference service chaiml-caesar-russian-m-37631-v1 to be ready
Inference service chaiml-caesar-russian-m-37631-v1 ready after 130.47636246681213s
Pipeline stage MKMLDeployer completed in 131.02s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.573091506958008s
Received healthy response to inference request in 2.1228082180023193s
Received healthy response to inference request in 1.9751226902008057s
Received healthy response to inference request in 2.0123631954193115s
Received healthy response to inference request in 2.1807782649993896s
5 requests
0 failed requests
5th percentile: 1.9825707912445067
10th percentile: 1.990018892288208
20th percentile: 2.0049150943756104
30th percentile: 2.034452199935913
40th percentile: 2.078630208969116
50th percentile: 2.1228082180023193
60th percentile: 2.1459962368011474
70th percentile: 2.1691842555999754
80th percentile: 2.2592409133911135
90th percentile: 2.4161662101745605
95th percentile: 2.494628858566284
99th percentile: 2.557398977279663
mean time: 2.1728327751159666
Pipeline stage StressChecker completed in 12.34s
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 0.73s
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 0.73s
Shutdown handler de-registered
chaiml-caesar-russian-m_37631_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 4851.77s
Shutdown handler de-registered
chaiml-caesar-russian-m_37631_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-caesar-russian-m_37631_v1 status is now torndown due to DeploymentManager action