submission_id: cgato-nemo-12b-theanswer_4750_v1
developer_uid: c.gato
best_of: 8
celo_rating: 1254.68
display_name: cgato-nemo-12b-theanswer_4750_v1
family_friendly_score: 0.562
family_friendly_standard_error: 0.00701649485141976
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-v0.1-E2
latencies: [{'batch_size': 1, 'throughput': 0.6282567665146206, 'latency_mean': 1.5916428077220917, 'latency_p50': 1.5991894006729126, 'latency_p90': 1.7649943113327027}, {'batch_size': 3, 'throughput': 1.1506223598976544, 'latency_mean': 2.5931037962436676, 'latency_p50': 2.602343797683716, 'latency_p90': 2.811353325843811}, {'batch_size': 5, 'throughput': 1.4005584123210448, 'latency_mean': 3.5503133654594423, 'latency_p50': 3.5425819158554077, 'latency_p90': 3.9849804162979128}, {'batch_size': 6, 'throughput': 1.488792313081164, 'latency_mean': 4.020002077817917, 'latency_p50': 4.0141884088516235, 'latency_p90': 4.500082159042358}, {'batch_size': 8, 'throughput': 1.5650723732686624, 'latency_mean': 5.068063514232636, 'latency_p50': 5.034111142158508, 'latency_p90': 5.6724780082702635}, {'batch_size': 10, 'throughput': 1.5960920938361522, 'latency_mean': 6.215891019105912, 'latency_p50': 6.205859303474426, 'latency_p90': 7.117577934265136}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: cgato/Nemo-12b-TheAnswer
model_name: cgato-nemo-12b-theanswer_4750_v1
model_num_parameters: 12772111360.0
model_repo: cgato/Nemo-12b-TheAnswer-v0.1-E2
model_size: 13B
num_battles: 11688
num_wins: 5917
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 1.44
timestamp: 2024-11-21T05:57:07+00:00
us_pacific_date: 2024-11-20
win_ratio: 0.5062457221081451
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-4750-v1-mkmlizer
Waiting for job on cgato-nemo-12b-theanswer-4750-v1-mkmlizer to finish
cgato-nemo-12b-theanswer-4750-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-nemo-12b-theanswer-4750-v1-mkmlizer: ║ _____ __ __ ║
cgato-nemo-12b-theanswer-4750-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-nemo-12b-theanswer-4750-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-nemo-12b-theanswer-4750-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-nemo-12b-theanswer-4750-v1-mkmlizer: ║ /___/ ║
cgato-nemo-12b-theanswer-4750-v1-mkmlizer: ║ ║
cgato-nemo-12b-theanswer-4750-v1-mkmlizer: ║ Version: 0.11.12 ║
cgato-nemo-12b-theanswer-4750-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-nemo-12b-theanswer-4750-v1-mkmlizer: ║ https://mk1.ai ║
cgato-nemo-12b-theanswer-4750-v1-mkmlizer: ║ ║
cgato-nemo-12b-theanswer-4750-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-nemo-12b-theanswer-4750-v1-mkmlizer: ║ belonging to: ║
cgato-nemo-12b-theanswer-4750-v1-mkmlizer: ║ ║
cgato-nemo-12b-theanswer-4750-v1-mkmlizer: ║ Chai Research Corp. ║
cgato-nemo-12b-theanswer-4750-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-nemo-12b-theanswer-4750-v1-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
cgato-nemo-12b-theanswer-4750-v1-mkmlizer: ║ ║
cgato-nemo-12b-theanswer-4750-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-nemo-12b-theanswer-4750-v1-mkmlizer: Downloaded to shared memory in 47.190s
cgato-nemo-12b-theanswer-4750-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpfiost6io, device:0
cgato-nemo-12b-theanswer-4750-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-nemo-12b-theanswer-4750-v1-mkmlizer: quantized model in 35.375s
cgato-nemo-12b-theanswer-4750-v1-mkmlizer: Processed model cgato/Nemo-12b-TheAnswer-v0.1-E2 in 82.565s
cgato-nemo-12b-theanswer-4750-v1-mkmlizer: creating bucket guanaco-mkml-models
cgato-nemo-12b-theanswer-4750-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-nemo-12b-theanswer-4750-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-nemo-12b-theanswer-4750-v1
cgato-nemo-12b-theanswer-4750-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-nemo-12b-theanswer-4750-v1/special_tokens_map.json
cgato-nemo-12b-theanswer-4750-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-nemo-12b-theanswer-4750-v1/config.json
cgato-nemo-12b-theanswer-4750-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-nemo-12b-theanswer-4750-v1/tokenizer_config.json
cgato-nemo-12b-theanswer-4750-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-nemo-12b-theanswer-4750-v1/tokenizer.json
cgato-nemo-12b-theanswer-4750-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-nemo-12b-theanswer-4750-v1/flywheel_model.0.safetensors
cgato-nemo-12b-theanswer-4750-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:11, 31.96it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:06, 54.11it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:06, 50.81it/s] Loading 0: 7%|▋ | 25/363 [00:00<00:06, 51.39it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 53.61it/s] Loading 0: 10%|█ | 37/363 [00:00<00:06, 50.54it/s] Loading 0: 12%|█▏ | 43/363 [00:00<00:06, 50.99it/s] Loading 0: 13%|█▎ | 49/363 [00:00<00:05, 53.24it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 49.60it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:08, 37.07it/s] Loading 0: 18%|█▊ | 66/363 [00:01<00:08, 36.79it/s] Loading 0: 20%|█▉ | 71/363 [00:01<00:07, 39.63it/s] Loading 0: 21%|██ | 76/363 [00:01<00:07, 39.45it/s] Loading 0: 22%|██▏ | 81/363 [00:01<00:07, 40.15it/s] Loading 0: 24%|██▎ | 86/363 [00:01<00:06, 41.26it/s] Loading 0: 25%|██▌ | 91/363 [00:02<00:07, 35.89it/s] Loading 0: 27%|██▋ | 99/363 [00:02<00:05, 45.15it/s] Loading 0: 29%|██▉ | 105/363 [00:02<00:05, 45.24it/s] Loading 0: 31%|███ | 112/363 [00:02<00:05, 50.19it/s] Loading 0: 33%|███▎ | 118/363 [00:02<00:05, 42.75it/s] Loading 0: 34%|███▍ | 125/363 [00:02<00:04, 48.65it/s] Loading 0: 36%|███▌ | 131/363 [00:02<00:04, 47.86it/s] Loading 0: 38%|███▊ | 137/363 [00:03<00:05, 43.76it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:06, 35.53it/s] Loading 0: 40%|████ | 146/363 [00:03<00:06, 36.14it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 35.35it/s] Loading 0: 43%|████▎ | 157/363 [00:03<00:04, 41.54it/s] Loading 0: 45%|████▍ | 163/363 [00:03<00:04, 42.55it/s] Loading 0: 46%|████▋ | 168/363 [00:03<00:04, 42.63it/s] Loading 0: 48%|████▊ | 174/363 [00:03<00:04, 46.50it/s] Loading 0: 49%|████▉ | 179/363 [00:04<00:04, 45.27it/s] Loading 0: 51%|█████ | 184/363 [00:04<00:03, 45.04it/s] Loading 0: 52%|█████▏ | 189/363 [00:04<00:03, 45.73it/s] Loading 0: 53%|█████▎ | 194/363 [00:04<00:04, 40.23it/s] Loading 0: 56%|█████▌ | 202/363 [00:04<00:03, 49.33it/s] Loading 0: 57%|█████▋ | 208/363 [00:04<00:03, 46.97it/s] Loading 0: 59%|█████▊ | 213/363 [00:04<00:03, 45.11it/s] Loading 0: 61%|██████ | 221/363 [00:04<00:02, 53.14it/s] Loading 0: 63%|██████▎ | 227/363 [00:05<00:03, 35.17it/s] Loading 0: 64%|██████▍ | 232/363 [00:05<00:03, 35.59it/s] Loading 0: 66%|██████▌ | 238/363 [00:05<00:03, 39.83it/s] Loading 0: 67%|██████▋ | 244/363 [00:05<00:02, 40.39it/s] Loading 0: 69%|██████▊ | 249/363 [00:05<00:02, 39.05it/s] Loading 0: 71%|███████ | 256/363 [00:05<00:02, 44.52it/s] Loading 0: 72%|███████▏ | 262/363 [00:06<00:02, 43.67it/s] Loading 0: 74%|███████▎ | 267/363 [00:06<00:02, 43.15it/s] Loading 0: 75%|███████▌ | 274/363 [00:06<00:01, 48.65it/s] Loading 0: 77%|███████▋ | 280/363 [00:06<00:01, 46.85it/s] Loading 0: 79%|███████▊ | 285/363 [00:06<00:01, 45.94it/s] Loading 0: 80%|████████ | 292/363 [00:06<00:01, 49.57it/s] Loading 0: 82%|████████▏ | 298/363 [00:06<00:01, 44.80it/s] Loading 0: 84%|████████▎ | 304/363 [00:13<00:20, 2.86it/s] Loading 0: 85%|████████▍ | 308/363 [00:13<00:15, 3.58it/s] Loading 0: 86%|████████▌ | 312/363 [00:13<00:11, 4.49it/s] Loading 0: 88%|████████▊ | 320/363 [00:13<00:05, 7.26it/s] Loading 0: 90%|████████▉ | 326/363 [00:14<00:03, 9.69it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:02, 12.17it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:01, 16.92it/s] Loading 0: 95%|█████████▍| 344/363 [00:14<00:00, 20.67it/s] Loading 0: 96%|█████████▌| 349/363 [00:14<00:00, 23.99it/s] Loading 0: 98%|█████████▊| 356/363 [00:14<00:00, 30.42it/s] Loading 0: 100%|█████████▉| 362/363 [00:14<00:00, 32.81it/s]
Job cgato-nemo-12b-theanswer-4750-v1-mkmlizer completed after 104.31s with status: succeeded
Stopping job with name cgato-nemo-12b-theanswer-4750-v1-mkmlizer
Pipeline stage MKMLizer completed in 105.02s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cgato-nemo-12b-theanswer-4750-v1
Waiting for inference service cgato-nemo-12b-theanswer-4750-v1 to be ready
Inference service cgato-nemo-12b-theanswer-4750-v1 ready after 261.95727729797363s
Pipeline stage MKMLDeployer completed in 262.58s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1480419635772705s
Received healthy response to inference request in 1.668555498123169s
Received healthy response to inference request in 1.790764331817627s
Received healthy response to inference request in 1.7763733863830566s
Received healthy response to inference request in 1.9461557865142822s
5 requests
0 failed requests
5th percentile: 1.6901190757751465
10th percentile: 1.7116826534271241
20th percentile: 1.754809808731079
30th percentile: 1.7792515754699707
40th percentile: 1.7850079536437988
50th percentile: 1.790764331817627
60th percentile: 1.852920913696289
70th percentile: 1.9150774955749512
80th percentile: 1.98653302192688
90th percentile: 2.067287492752075
95th percentile: 2.1076647281646728
99th percentile: 2.139966516494751
mean time: 1.865978193283081
Pipeline stage StressChecker completed in 10.97s
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 5.83s
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 2.48s
Shutdown handler de-registered
cgato-nemo-12b-theanswer_4750_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 2737.28s
Shutdown handler de-registered
cgato-nemo-12b-theanswer_4750_v1 status is now inactive due to auto deactivation removed underperforming models