submission_id: rinen0721-mistral12b-exp2_v2
developer_uid: rinen0721
best_of: 8
celo_rating: 1241.28
display_name: rinen0721-mistral12b-exp2_v1
family_friendly_score: 0.5651999999999999
family_friendly_standard_error: 0.007010691264062339
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}
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}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: False
language_model: rinen0721/Mistral12b-exp2
latencies: [{'batch_size': 1, 'throughput': 0.6082852008409616, 'latency_mean': 1.6438981664180756, 'latency_p50': 1.6558581590652466, 'latency_p90': 1.8074597120285034}, {'batch_size': 3, 'throughput': 1.130406313695541, 'latency_mean': 2.64732412815094, 'latency_p50': 2.6444029808044434, 'latency_p90': 2.897249889373779}, {'batch_size': 5, 'throughput': 1.3642636387283187, 'latency_mean': 3.6379332053661346, 'latency_p50': 3.6332606077194214, 'latency_p90': 4.046277594566345}, {'batch_size': 6, 'throughput': 1.4307755516035225, 'latency_mean': 4.164207681417465, 'latency_p50': 4.169880747795105, 'latency_p90': 4.6188366413116455}, {'batch_size': 8, 'throughput': 1.5102229915231682, 'latency_mean': 5.263955441713333, 'latency_p50': 5.254937171936035, 'latency_p90': 5.901759481430053}, {'batch_size': 10, 'throughput': 1.5499540745753098, 'latency_mean': 6.405769987106323, 'latency_p50': 6.407044529914856, 'latency_p90': 7.229660630226135}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: rinen0721/Mistral12b-exp
model_name: rinen0721-mistral12b-exp2_v1
model_num_parameters: 12772070400.0
model_repo: rinen0721/Mistral12b-exp2
model_size: 13B
num_battles: 14032
num_wins: 6948
ranking_group: single
status: torndown
submission_type: basic
throughput_3p7s: 1.38
timestamp: 2024-11-12T09:43:09+00:00
us_pacific_date: 2024-11-12
win_ratio: 0.4951539338654504
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 rinen0721-mistral12b-exp2-v2-mkmlizer
Waiting for job on rinen0721-mistral12b-exp2-v2-mkmlizer to finish
rinen0721-mistral12b-exp2-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rinen0721-mistral12b-exp2-v2-mkmlizer: ║ _____ __ __ ║
rinen0721-mistral12b-exp2-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rinen0721-mistral12b-exp2-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rinen0721-mistral12b-exp2-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rinen0721-mistral12b-exp2-v2-mkmlizer: ║ /___/ ║
rinen0721-mistral12b-exp2-v2-mkmlizer: ║ ║
rinen0721-mistral12b-exp2-v2-mkmlizer: ║ Version: 0.11.33 ║
rinen0721-mistral12b-exp2-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rinen0721-mistral12b-exp2-v2-mkmlizer: ║ https://mk1.ai ║
rinen0721-mistral12b-exp2-v2-mkmlizer: ║ ║
rinen0721-mistral12b-exp2-v2-mkmlizer: ║ The license key for the current software has been verified as ║
rinen0721-mistral12b-exp2-v2-mkmlizer: ║ belonging to: ║
rinen0721-mistral12b-exp2-v2-mkmlizer: ║ ║
rinen0721-mistral12b-exp2-v2-mkmlizer: ║ Chai Research Corp. ║
rinen0721-mistral12b-exp2-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rinen0721-mistral12b-exp2-v2-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
rinen0721-mistral12b-exp2-v2-mkmlizer: ║ ║
rinen0721-mistral12b-exp2-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rinen0721-mistral12b-exp2-v2-mkmlizer: Downloaded to shared memory in 46.130s
rinen0721-mistral12b-exp2-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpvfzq5hid, device:0
rinen0721-mistral12b-exp2-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rinen0721-mistral12b-exp2-v2-mkmlizer: quantized model in 39.552s
rinen0721-mistral12b-exp2-v2-mkmlizer: Processed model rinen0721/Mistral12b-exp2 in 85.682s
rinen0721-mistral12b-exp2-v2-mkmlizer: creating bucket guanaco-mkml-models
rinen0721-mistral12b-exp2-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rinen0721-mistral12b-exp2-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rinen0721-mistral12b-exp2-v2
rinen0721-mistral12b-exp2-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rinen0721-mistral12b-exp2-v2/config.json
rinen0721-mistral12b-exp2-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rinen0721-mistral12b-exp2-v2/special_tokens_map.json
rinen0721-mistral12b-exp2-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rinen0721-mistral12b-exp2-v2/tokenizer_config.json
rinen0721-mistral12b-exp2-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rinen0721-mistral12b-exp2-v2/tokenizer.json
rinen0721-mistral12b-exp2-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rinen0721-mistral12b-exp2-v2/flywheel_model.0.safetensors
rinen0721-mistral12b-exp2-v2-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:13, 27.40it/s] Loading 0: 3%|▎ | 12/363 [00:00<00:08, 43.16it/s] Loading 0: 5%|▍ | 17/363 [00:00<00:08, 40.20it/s] Loading 0: 6%|▌ | 22/363 [00:00<00:08, 39.28it/s] Loading 0: 7%|▋ | 27/363 [00:00<00:08, 40.08it/s] Loading 0: 9%|▉ | 32/363 [00:00<00:10, 31.54it/s] Loading 0: 11%|█ | 39/363 [00:01<00:08, 39.08it/s] Loading 0: 12%|█▏ | 44/363 [00:01<00:08, 38.49it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:08, 38.65it/s] Loading 0: 15%|█▍ | 54/363 [00:01<00:07, 40.52it/s] Loading 0: 16%|█▋ | 59/363 [00:01<00:07, 42.48it/s] Loading 0: 18%|█▊ | 64/363 [00:01<00:12, 23.82it/s] Loading 0: 20%|█▉ | 71/363 [00:02<00:09, 30.71it/s] Loading 0: 21%|██ | 76/363 [00:02<00:08, 32.17it/s] Loading 0: 22%|██▏ | 81/363 [00:02<00:08, 33.63it/s] Loading 0: 23%|██▎ | 85/363 [00:02<00:08, 34.13it/s] Loading 0: 25%|██▍ | 89/363 [00:02<00:07, 34.76it/s] Loading 0: 26%|██▌ | 93/363 [00:02<00:08, 33.61it/s] Loading 0: 27%|██▋ | 98/363 [00:02<00:07, 36.42it/s] Loading 0: 28%|██▊ | 102/363 [00:02<00:07, 35.06it/s] Loading 0: 29%|██▉ | 106/363 [00:03<00:07, 34.25it/s] Loading 0: 31%|███ | 112/363 [00:03<00:06, 38.07it/s] Loading 0: 32%|███▏ | 116/363 [00:03<00:07, 34.81it/s] Loading 0: 33%|███▎ | 120/363 [00:03<00:07, 33.02it/s] Loading 0: 34%|███▍ | 124/363 [00:03<00:06, 34.56it/s] Loading 0: 35%|███▌ | 128/363 [00:03<00:07, 30.95it/s] Loading 0: 36%|███▋ | 132/363 [00:03<00:07, 32.76it/s] Loading 0: 37%|███▋ | 136/363 [00:03<00:07, 29.91it/s] Loading 0: 39%|███▉ | 141/363 [00:04<00:06, 33.95it/s] Loading 0: 40%|███▉ | 145/363 [00:04<00:10, 21.77it/s] Loading 0: 41%|████ | 149/363 [00:04<00:09, 21.95it/s] Loading 0: 42%|████▏ | 154/363 [00:04<00:07, 26.55it/s] Loading 0: 44%|████▎ | 158/363 [00:04<00:07, 25.89it/s] Loading 0: 45%|████▍ | 163/363 [00:04<00:06, 30.38it/s] Loading 0: 46%|████▌ | 167/363 [00:05<00:06, 28.18it/s] Loading 0: 47%|████▋ | 172/363 [00:05<00:05, 32.17it/s] Loading 0: 48%|████▊ | 176/363 [00:05<00:06, 29.91it/s] Loading 0: 50%|████▉ | 181/363 [00:05<00:05, 33.82it/s] Loading 0: 51%|█████ | 185/363 [00:05<00:05, 30.16it/s] Loading 0: 52%|█████▏ | 190/363 [00:05<00:05, 34.08it/s] Loading 0: 53%|█████▎ | 194/363 [00:05<00:05, 30.78it/s] Loading 0: 55%|█████▍ | 199/363 [00:06<00:04, 33.16it/s] Loading 0: 56%|█████▌ | 203/363 [00:06<00:05, 30.17it/s] Loading 0: 57%|█████▋ | 208/363 [00:06<00:04, 34.35it/s] Loading 0: 58%|█████▊ | 212/363 [00:06<00:04, 30.98it/s] Loading 0: 60%|█████▉ | 217/363 [00:06<00:04, 34.98it/s] Loading 0: 61%|██████ | 222/363 [00:06<00:03, 37.04it/s] Loading 0: 62%|██████▏ | 226/363 [00:07<00:05, 23.65it/s] Loading 0: 63%|██████▎ | 230/363 [00:07<00:05, 24.33it/s] Loading 0: 65%|██████▌ | 237/363 [00:07<00:04, 31.48it/s] Loading 0: 66%|██████▋ | 241/363 [00:07<00:03, 31.20it/s] Loading 0: 67%|██████▋ | 245/363 [00:07<00:03, 33.06it/s] Loading 0: 69%|██████▊ | 249/363 [00:07<00:03, 30.82it/s] Loading 0: 70%|██████▉ | 253/363 [00:07<00:03, 32.66it/s] Loading 0: 71%|███████ | 257/363 [00:08<00:03, 29.37it/s] Loading 0: 72%|███████▏ | 262/363 [00:08<00:02, 33.80it/s] Loading 0: 73%|███████▎ | 266/363 [00:08<00:03, 30.91it/s] Loading 0: 75%|███████▍ | 271/363 [00:08<00:02, 34.80it/s] Loading 0: 76%|███████▌ | 275/363 [00:08<00:02, 31.39it/s] Loading 0: 78%|███████▊ | 282/363 [00:08<00:02, 38.14it/s] Loading 0: 79%|███████▉ | 287/363 [00:08<00:02, 36.66it/s] Loading 0: 80%|████████ | 291/363 [00:08<00:02, 35.24it/s] Loading 0: 81%|████████▏ | 295/363 [00:09<00:02, 33.11it/s] Loading 0: 82%|████████▏ | 299/363 [00:09<00:01, 32.69it/s] Loading 0: 84%|████████▎ | 304/363 [00:16<00:28, 2.07it/s] Loading 0: 85%|████████▍ | 307/363 [00:16<00:21, 2.59it/s] Loading 0: 86%|████████▌ | 312/363 [00:16<00:13, 3.79it/s] Loading 0: 88%|████████▊ | 319/363 [00:16<00:07, 6.12it/s] Loading 0: 89%|████████▉ | 323/363 [00:16<00:05, 7.65it/s] Loading 0: 90%|█████████ | 328/363 [00:16<00:03, 10.25it/s] Loading 0: 91%|█████████▏| 332/363 [00:17<00:02, 12.51it/s] Loading 0: 93%|█████████▎| 337/363 [00:17<00:01, 16.41it/s] Loading 0: 94%|█████████▍| 342/363 [00:17<00:01, 19.83it/s] Loading 0: 95%|█████████▌| 346/363 [00:17<00:00, 22.40it/s] Loading 0: 96%|█████████▋| 350/363 [00:17<00:00, 24.29it/s] Loading 0: 98%|█████████▊| 355/363 [00:17<00:00, 28.87it/s] Loading 0: 99%|█████████▉| 359/363 [00:17<00:00, 29.72it/s]
Job rinen0721-mistral12b-exp2-v2-mkmlizer completed after 114.05s with status: succeeded
Stopping job with name rinen0721-mistral12b-exp2-v2-mkmlizer
Pipeline stage MKMLizer completed in 114.54s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.21s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rinen0721-mistral12b-exp2-v2
Waiting for inference service rinen0721-mistral12b-exp2-v2 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service rinen0721-mistral12b-exp2-v2 ready after 241.64410948753357s
Pipeline stage MKMLDeployer completed in 242.18s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.043699026107788s
Received healthy response to inference request in 1.6701462268829346s
Received healthy response to inference request in 1.6619057655334473s
Received healthy response to inference request in 1.5379717350006104s
Received healthy response to inference request in 1.2028405666351318s
5 requests
0 failed requests
5th percentile: 1.2698668003082276
10th percentile: 1.3368930339813232
20th percentile: 1.4709455013275146
30th percentile: 1.5627585411071778
40th percentile: 1.6123321533203125
50th percentile: 1.6619057655334473
60th percentile: 1.6652019500732422
70th percentile: 1.6684981346130372
80th percentile: 1.7448567867279055
90th percentile: 1.8942779064178468
95th percentile: 1.9689884662628172
99th percentile: 2.028756914138794
mean time: 1.6233126640319824
Pipeline stage StressChecker completed in 9.89s
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 5.17s
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 2.01s
Shutdown handler de-registered
rinen0721-mistral12b-exp2_v2 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 2853.84s
Shutdown handler de-registered
rinen0721-mistral12b-exp2_v2 status is now inactive due to auto deactivation removed underperforming models
rinen0721-mistral12b-exp2_v2 status is now torndown due to DeploymentManager action