submission_id: cgato-nemo-12b-theanswer_9611_v1
developer_uid: c.gato
best_of: 8
celo_rating: 1247.96
display_name: cgato-nemo-12b-theanswer_9611_v1
family_friendly_score: 0.5588
family_friendly_standard_error: 0.007022001993733695
formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{bot_name}:', 'truncate_by_message': True}
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: cgato/Nemo-12b-TheAnswer-v0.2-E2
latencies: [{'batch_size': 1, 'throughput': 0.6160698000380902, 'latency_mean': 1.6231343126296998, 'latency_p50': 1.6073347330093384, 'latency_p90': 1.799790048599243}, {'batch_size': 3, 'throughput': 1.1343161427051536, 'latency_mean': 2.6425792825222016, 'latency_p50': 2.630568265914917, 'latency_p90': 2.924852752685547}, {'batch_size': 5, 'throughput': 1.3628695606335697, 'latency_mean': 3.655720154047012, 'latency_p50': 3.6672592163085938, 'latency_p90': 4.0584405899047855}, {'batch_size': 6, 'throughput': 1.4443270743051284, 'latency_mean': 4.13547024011612, 'latency_p50': 4.140810251235962, 'latency_p90': 4.704245495796203}, {'batch_size': 8, 'throughput': 1.50941209834946, 'latency_mean': 5.261512570381164, 'latency_p50': 5.295159816741943, 'latency_p90': 5.8966917276382445}, {'batch_size': 10, 'throughput': 1.543974346675165, 'latency_mean': 6.448635407686234, 'latency_p50': 6.494902968406677, 'latency_p90': 7.113362884521484}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: cgato/Nemo-12b-TheAnswer
model_name: cgato-nemo-12b-theanswer_9611_v1
model_num_parameters: 12772111360.0
model_repo: cgato/Nemo-12b-TheAnswer-v0.2-E2
model_size: 13B
num_battles: 11487
num_wins: 5706
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 1.38
timestamp: 2024-11-22T02:10:39+00:00
us_pacific_date: 2024-11-21
win_ratio: 0.49673544006267956
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 cgato-nemo-12b-theanswer-9611-v1-mkmlizer
Waiting for job on cgato-nemo-12b-theanswer-9611-v1-mkmlizer to finish
cgato-nemo-12b-theanswer-9611-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-nemo-12b-theanswer-9611-v1-mkmlizer: ║ _____ __ __ ║
cgato-nemo-12b-theanswer-9611-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-nemo-12b-theanswer-9611-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-nemo-12b-theanswer-9611-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-nemo-12b-theanswer-9611-v1-mkmlizer: ║ /___/ ║
cgato-nemo-12b-theanswer-9611-v1-mkmlizer: ║ ║
cgato-nemo-12b-theanswer-9611-v1-mkmlizer: ║ Version: 0.11.12 ║
cgato-nemo-12b-theanswer-9611-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-nemo-12b-theanswer-9611-v1-mkmlizer: ║ https://mk1.ai ║
cgato-nemo-12b-theanswer-9611-v1-mkmlizer: ║ ║
cgato-nemo-12b-theanswer-9611-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-nemo-12b-theanswer-9611-v1-mkmlizer: ║ belonging to: ║
cgato-nemo-12b-theanswer-9611-v1-mkmlizer: ║ ║
cgato-nemo-12b-theanswer-9611-v1-mkmlizer: ║ Chai Research Corp. ║
cgato-nemo-12b-theanswer-9611-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-nemo-12b-theanswer-9611-v1-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
cgato-nemo-12b-theanswer-9611-v1-mkmlizer: ║ ║
cgato-nemo-12b-theanswer-9611-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-nemo-12b-theanswer-9611-v1-mkmlizer: Downloaded to shared memory in 53.369s
cgato-nemo-12b-theanswer-9611-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp4zzkmace, device:0
cgato-nemo-12b-theanswer-9611-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-nemo-12b-theanswer-9611-v1-mkmlizer: quantized model in 36.614s
cgato-nemo-12b-theanswer-9611-v1-mkmlizer: Processed model cgato/Nemo-12b-TheAnswer-v0.2-E2 in 89.983s
cgato-nemo-12b-theanswer-9611-v1-mkmlizer: creating bucket guanaco-mkml-models
cgato-nemo-12b-theanswer-9611-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-nemo-12b-theanswer-9611-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-nemo-12b-theanswer-9611-v1
cgato-nemo-12b-theanswer-9611-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-nemo-12b-theanswer-9611-v1/config.json
cgato-nemo-12b-theanswer-9611-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-nemo-12b-theanswer-9611-v1/special_tokens_map.json
cgato-nemo-12b-theanswer-9611-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-nemo-12b-theanswer-9611-v1/tokenizer_config.json
cgato-nemo-12b-theanswer-9611-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-nemo-12b-theanswer-9611-v1/tokenizer.json
cgato-nemo-12b-theanswer-9611-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-nemo-12b-theanswer-9611-v1/flywheel_model.0.safetensors
cgato-nemo-12b-theanswer-9611-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:11, 31.23it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:06, 50.17it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 45.07it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:07, 43.44it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 48.64it/s] Loading 0: 10%|█ | 37/363 [00:00<00:07, 44.72it/s] Loading 0: 12%|█▏ | 42/363 [00:00<00:07, 43.46it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:06, 48.52it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 45.87it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:08, 33.78it/s] Loading 0: 18%|█▊ | 65/363 [00:01<00:09, 32.98it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 39.24it/s] Loading 0: 21%|██ | 77/363 [00:01<00:06, 41.51it/s] Loading 0: 23%|██▎ | 82/363 [00:02<00:07, 35.57it/s] Loading 0: 25%|██▍ | 89/363 [00:02<00:06, 42.40it/s] Loading 0: 26%|██▌ | 94/363 [00:02<00:06, 42.17it/s] Loading 0: 27%|██▋ | 99/363 [00:02<00:06, 42.63it/s] Loading 0: 29%|██▊ | 104/363 [00:02<00:05, 44.08it/s] Loading 0: 30%|███ | 110/363 [00:02<00:06, 41.53it/s] Loading 0: 32%|███▏ | 115/363 [00:02<00:05, 41.77it/s] Loading 0: 33%|███▎ | 120/363 [00:02<00:06, 40.43it/s] Loading 0: 34%|███▍ | 125/363 [00:02<00:05, 42.67it/s] Loading 0: 36%|███▌ | 130/363 [00:03<00:05, 41.70it/s] Loading 0: 37%|███▋ | 135/363 [00:03<00:05, 41.77it/s] Loading 0: 39%|███▊ | 140/363 [00:03<00:05, 42.90it/s] Loading 0: 40%|███▉ | 145/363 [00:03<00:08, 25.37it/s] Loading 0: 41%|████ | 149/363 [00:03<00:08, 26.37it/s] Loading 0: 43%|████▎ | 156/363 [00:03<00:06, 34.08it/s] Loading 0: 44%|████▍ | 161/363 [00:04<00:05, 36.06it/s] Loading 0: 46%|████▌ | 166/363 [00:04<00:05, 37.45it/s] Loading 0: 47%|████▋ | 171/363 [00:04<00:04, 39.88it/s] Loading 0: 48%|████▊ | 176/363 [00:04<00:05, 33.17it/s] Loading 0: 50%|█████ | 183/363 [00:04<00:04, 40.40it/s] Loading 0: 52%|█████▏ | 188/363 [00:04<00:04, 41.18it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:04, 42.33it/s] Loading 0: 55%|█████▍ | 198/363 [00:04<00:03, 43.99it/s] Loading 0: 56%|█████▌ | 203/363 [00:05<00:04, 34.42it/s] Loading 0: 58%|█████▊ | 210/363 [00:05<00:03, 41.35it/s] Loading 0: 59%|█████▉ | 215/363 [00:05<00:03, 41.64it/s] Loading 0: 61%|██████ | 220/363 [00:05<00:03, 43.50it/s] Loading 0: 62%|██████▏ | 225/363 [00:05<00:05, 26.95it/s] Loading 0: 63%|██████▎ | 230/363 [00:06<00:04, 29.37it/s] Loading 0: 65%|██████▌ | 237/363 [00:06<00:03, 35.99it/s] Loading 0: 67%|██████▋ | 242/363 [00:06<00:03, 36.86it/s] Loading 0: 68%|██████▊ | 247/363 [00:06<00:03, 38.02it/s] Loading 0: 69%|██████▉ | 252/363 [00:06<00:02, 40.49it/s] Loading 0: 71%|███████ | 257/363 [00:06<00:03, 32.79it/s] Loading 0: 73%|███████▎ | 264/363 [00:06<00:02, 39.63it/s] Loading 0: 74%|███████▍ | 269/363 [00:06<00:02, 40.20it/s] Loading 0: 75%|███████▌ | 274/363 [00:07<00:02, 41.25it/s] Loading 0: 77%|███████▋ | 279/363 [00:07<00:01, 42.28it/s] Loading 0: 78%|███████▊ | 284/363 [00:07<00:02, 34.36it/s] Loading 0: 80%|████████ | 291/363 [00:07<00:01, 40.51it/s] Loading 0: 82%|████████▏ | 296/363 [00:07<00:01, 40.64it/s] Loading 0: 83%|████████▎ | 301/363 [00:07<00:01, 42.18it/s] Loading 0: 84%|████████▍ | 306/363 [00:14<00:23, 2.45it/s] Loading 0: 85%|████████▌ | 310/363 [00:14<00:16, 3.14it/s] Loading 0: 86%|████████▌ | 313/363 [00:14<00:12, 3.85it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:06, 6.24it/s] Loading 0: 90%|████████▉ | 325/363 [00:15<00:04, 8.41it/s] Loading 0: 91%|█████████ | 330/363 [00:15<00:03, 10.45it/s] Loading 0: 93%|█████████▎| 337/363 [00:15<00:01, 15.21it/s] Loading 0: 94%|█████████▍| 342/363 [00:15<00:01, 18.46it/s] Loading 0: 96%|█████████▌| 347/363 [00:15<00:00, 22.14it/s] Loading 0: 97%|█████████▋| 352/363 [00:15<00:00, 26.31it/s] Loading 0: 98%|█████████▊| 357/363 [00:15<00:00, 26.47it/s]
Job cgato-nemo-12b-theanswer-9611-v1-mkmlizer completed after 116.95s with status: succeeded
Stopping job with name cgato-nemo-12b-theanswer-9611-v1-mkmlizer
Pipeline stage MKMLizer completed in 118.25s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.56s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cgato-nemo-12b-theanswer-9611-v1
Waiting for inference service cgato-nemo-12b-theanswer-9611-v1 to be ready
Retrying (%r) after connection broken by '%r': %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 cgato-nemo-12b-theanswer-9611-v1 ready after 230.91839623451233s
Pipeline stage MKMLDeployer completed in 231.43s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 1.8418116569519043s
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
Received healthy response to inference request in 1.684096336364746s
Received healthy response to inference request in 1.3662419319152832s
Received healthy response to inference request in 1.7762508392333984s
5 requests
1 failed requests
5th percentile: 1.4298128128051757
10th percentile: 1.4933836936950684
20th percentile: 1.6205254554748536
30th percentile: 1.7025272369384765
40th percentile: 1.7393890380859376
50th percentile: 1.7762508392333984
60th percentile: 1.8024751663208007
70th percentile: 1.828699493408203
80th percentile: 5.519054889678959
90th percentile: 12.873541355133058
95th percentile: 16.550784587860104
99th percentile: 19.492579174041747
mean time: 5.379285717010498
%s, retrying in %s seconds...
Received healthy response to inference request in 1.7243611812591553s
Received healthy response to inference request in 1.8347737789154053s
Received healthy response to inference request in 1.755615234375s
Received healthy response to inference request in 1.7598693370819092s
Received healthy response to inference request in 2.4696526527404785s
5 requests
0 failed requests
5th percentile: 1.7306119918823242
10th percentile: 1.736862802505493
20th percentile: 1.749364423751831
30th percentile: 1.7564660549163817
40th percentile: 1.7581676959991455
50th percentile: 1.7598693370819092
60th percentile: 1.7898311138153076
70th percentile: 1.819792890548706
80th percentile: 1.96174955368042
90th percentile: 2.215701103210449
95th percentile: 2.342676877975464
99th percentile: 2.4442574977874756
mean time: 1.9088544368743896
Pipeline stage StressChecker completed in 39.51s
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 2.42s
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 2.57s
Shutdown handler de-registered
cgato-nemo-12b-theanswer_9611_v1 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 0.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cgato-nemo-12b-theanswer-9611-v1-profiler
Waiting for inference service cgato-nemo-12b-theanswer-9611-v1-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 2672.70s
Shutdown handler de-registered
cgato-nemo-12b-theanswer_9611_v1 status is now inactive due to auto deactivation removed underperforming models