submission_id: cgato-nemo-12b-thespice-_1853_v3
developer_uid: c.gato
best_of: 8
celo_rating: 1243.34
display_name: cgato-nemo-12b-thespice-_1853_v3
family_friendly_score: 0.5742
family_friendly_standard_error: 0.00699277284058334
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-TheSpice-V0.9-All-v2-KTO-v0.3-Small-2k
latencies: [{'batch_size': 1, 'throughput': 0.60800712628958, 'latency_mean': 1.6446201407909393, 'latency_p50': 1.6437314748764038, 'latency_p90': 1.815349006652832}, {'batch_size': 3, 'throughput': 1.1103142611502024, 'latency_mean': 2.69559427857399, 'latency_p50': 2.684040069580078, 'latency_p90': 2.939906430244446}, {'batch_size': 5, 'throughput': 1.3447409134416544, 'latency_mean': 3.695742506980896, 'latency_p50': 3.7083897590637207, 'latency_p90': 4.225240421295166}, {'batch_size': 6, 'throughput': 1.4035493575372968, 'latency_mean': 4.250467154979706, 'latency_p50': 4.277415156364441, 'latency_p90': 4.694267225265503}, {'batch_size': 8, 'throughput': 1.4892502124983653, 'latency_mean': 5.344818552732468, 'latency_p50': 5.340111255645752, 'latency_p90': 6.025803136825561}, {'batch_size': 10, 'throughput': 1.5185309346845324, 'latency_mean': 6.5403283095359805, 'latency_p50': 6.501594424247742, 'latency_p90': 7.39881706237793}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: cgato/Nemo-12b-TheSpice-
model_name: cgato-nemo-12b-thespice-_1853_v3
model_num_parameters: 12772121600.0
model_repo: cgato/Nemo-12b-TheSpice-V0.9-All-v2-KTO-v0.3-Small-2k
model_size: 13B
num_battles: 8767
num_wins: 4352
ranking_group: single
status: torndown
submission_type: basic
throughput_3p7s: 1.35
timestamp: 2024-11-13T02:19:48+00:00
us_pacific_date: 2024-11-12
win_ratio: 0.4964069807231664
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-thespice-1853-v3-mkmlizer
Waiting for job on cgato-nemo-12b-thespice-1853-v3-mkmlizer to finish
cgato-nemo-12b-thespice-1853-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-nemo-12b-thespice-1853-v3-mkmlizer: ║ _____ __ __ ║
cgato-nemo-12b-thespice-1853-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-nemo-12b-thespice-1853-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-nemo-12b-thespice-1853-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-nemo-12b-thespice-1853-v3-mkmlizer: ║ /___/ ║
cgato-nemo-12b-thespice-1853-v3-mkmlizer: ║ ║
cgato-nemo-12b-thespice-1853-v3-mkmlizer: ║ Version: 0.11.33 ║
cgato-nemo-12b-thespice-1853-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-nemo-12b-thespice-1853-v3-mkmlizer: ║ https://mk1.ai ║
cgato-nemo-12b-thespice-1853-v3-mkmlizer: ║ ║
cgato-nemo-12b-thespice-1853-v3-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-nemo-12b-thespice-1853-v3-mkmlizer: ║ belonging to: ║
cgato-nemo-12b-thespice-1853-v3-mkmlizer: ║ ║
cgato-nemo-12b-thespice-1853-v3-mkmlizer: ║ Chai Research Corp. ║
cgato-nemo-12b-thespice-1853-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-nemo-12b-thespice-1853-v3-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
cgato-nemo-12b-thespice-1853-v3-mkmlizer: ║ ║
cgato-nemo-12b-thespice-1853-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Failed to get response for submission blend_namot_2024-11-13: ('http://blend-mifir-2024-11-13-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '{"detail":"Gateway Timeout"}')
cgato-nemo-12b-thespice-1853-v3-mkmlizer: Downloaded to shared memory in 117.828s
cgato-nemo-12b-thespice-1853-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp7hz78b0d, device:0
cgato-nemo-12b-thespice-1853-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-nemo-12b-thespice-1853-v3-mkmlizer: quantized model in 37.824s
cgato-nemo-12b-thespice-1853-v3-mkmlizer: Processed model cgato/Nemo-12b-TheSpice-V0.9-All-v2-KTO-v0.3-Small-2k in 155.652s
cgato-nemo-12b-thespice-1853-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-nemo-12b-thespice-1853-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-nemo-12b-thespice-1853-v3
cgato-nemo-12b-thespice-1853-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-nemo-12b-thespice-1853-v3/config.json
cgato-nemo-12b-thespice-1853-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-nemo-12b-thespice-1853-v3/special_tokens_map.json
cgato-nemo-12b-thespice-1853-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-nemo-12b-thespice-1853-v3/tokenizer_config.json
cgato-nemo-12b-thespice-1853-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-nemo-12b-thespice-1853-v3/tokenizer.json
cgato-nemo-12b-thespice-1853-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-nemo-12b-thespice-1853-v3/flywheel_model.0.safetensors
cgato-nemo-12b-thespice-1853-v3-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:13, 27.07it/s] Loading 0: 3%|▎ | 12/363 [00:00<00:07, 43.96it/s] Loading 0: 5%|▍ | 17/363 [00:00<00:08, 42.22it/s] Loading 0: 6%|▌ | 22/363 [00:00<00:08, 42.32it/s] Loading 0: 7%|▋ | 27/363 [00:00<00:07, 44.44it/s] Loading 0: 9%|▉ | 32/363 [00:00<00:08, 37.47it/s] Loading 0: 11%|█ | 39/363 [00:00<00:07, 44.29it/s] Loading 0: 12%|█▏ | 44/363 [00:01<00:07, 43.37it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:07, 43.77it/s] Loading 0: 15%|█▍ | 54/363 [00:01<00:06, 44.28it/s] Loading 0: 16%|█▋ | 59/363 [00:01<00:06, 43.70it/s] Loading 0: 18%|█▊ | 64/363 [00:01<00:12, 24.42it/s] Loading 0: 20%|█▉ | 71/363 [00:01<00:09, 32.24it/s] Loading 0: 21%|██ | 76/363 [00:02<00:08, 33.38it/s] Loading 0: 22%|██▏ | 81/363 [00:02<00:08, 35.14it/s] Loading 0: 24%|██▎ | 86/363 [00:02<00:07, 37.38it/s] Loading 0: 25%|██▌ | 91/363 [00:02<00:08, 30.96it/s] Loading 0: 26%|██▋ | 96/363 [00:02<00:07, 34.08it/s] Loading 0: 28%|██▊ | 100/363 [00:02<00:08, 32.25it/s] Loading 0: 29%|██▉ | 106/363 [00:02<00:06, 37.61it/s] Loading 0: 31%|███ | 112/363 [00:02<00:06, 41.41it/s] Loading 0: 32%|███▏ | 117/363 [00:03<00:06, 39.04it/s] Loading 0: 34%|███▎ | 122/363 [00:03<00:06, 39.75it/s] Loading 0: 35%|███▍ | 127/363 [00:03<00:07, 33.06it/s] Loading 0: 37%|███▋ | 134/363 [00:03<00:05, 39.73it/s] Loading 0: 38%|███▊ | 139/363 [00:03<00:05, 39.44it/s] Loading 0: 40%|███▉ | 144/363 [00:04<00:08, 25.17it/s] Loading 0: 41%|████ | 149/363 [00:04<00:07, 27.46it/s] Loading 0: 43%|████▎ | 156/363 [00:04<00:05, 35.12it/s] Loading 0: 44%|████▍ | 161/363 [00:04<00:05, 36.86it/s] Loading 0: 46%|████▌ | 166/363 [00:04<00:05, 38.55it/s] Loading 0: 47%|████▋ | 171/363 [00:04<00:04, 40.68it/s] Loading 0: 48%|████▊ | 176/363 [00:04<00:05, 35.41it/s] Loading 0: 51%|█████ | 184/363 [00:04<00:04, 43.39it/s] Loading 0: 52%|█████▏ | 189/363 [00:05<00:03, 43.70it/s] Loading 0: 53%|█████▎ | 194/363 [00:05<00:04, 37.87it/s] Loading 0: 56%|█████▌ | 202/363 [00:05<00:03, 45.35it/s] Loading 0: 57%|█████▋ | 207/363 [00:05<00:03, 45.46it/s] Loading 0: 58%|█████▊ | 212/363 [00:05<00:03, 37.88it/s] Loading 0: 60%|██████ | 218/363 [00:05<00:03, 42.60it/s] Loading 0: 61%|██████▏ | 223/363 [00:06<00:04, 32.00it/s] Loading 0: 63%|██████▎ | 227/363 [00:06<00:04, 32.50it/s] Loading 0: 64%|██████▎ | 231/363 [00:06<00:04, 30.99it/s] Loading 0: 65%|██████▌ | 237/363 [00:06<00:03, 35.81it/s] Loading 0: 66%|██████▋ | 241/363 [00:06<00:03, 35.94it/s] Loading 0: 68%|██████▊ | 247/363 [00:06<00:02, 40.19it/s] Loading 0: 69%|██████▉ | 252/363 [00:06<00:02, 41.91it/s] Loading 0: 71%|███████ | 257/363 [00:06<00:02, 35.93it/s] Loading 0: 73%|███████▎ | 265/363 [00:07<00:02, 44.24it/s] Loading 0: 74%|███████▍ | 270/363 [00:07<00:02, 45.53it/s] Loading 0: 76%|███████▌ | 275/363 [00:07<00:02, 38.63it/s] Loading 0: 78%|███████▊ | 282/363 [00:07<00:01, 44.94it/s] Loading 0: 79%|███████▉ | 287/363 [00:07<00:01, 44.56it/s] Loading 0: 80%|████████ | 292/363 [00:07<00:01, 44.78it/s] Loading 0: 82%|████████▏ | 297/363 [00:07<00:01, 45.47it/s] Loading 0: 83%|████████▎ | 303/363 [00:07<00:01, 43.56it/s] Loading 0: 85%|████████▍ | 308/363 [00:15<00:22, 2.42it/s] Loading 0: 86%|████████▌ | 312/363 [00:15<00:16, 3.08it/s] Loading 0: 88%|████████▊ | 320/363 [00:15<00:08, 5.07it/s] Loading 0: 90%|████████▉ | 326/363 [00:15<00:05, 6.93it/s] Loading 0: 91%|█████████ | 331/363 [00:15<00:03, 8.90it/s] Loading 0: 93%|█████████▎| 338/363 [00:15<00:01, 12.67it/s] Loading 0: 95%|█████████▍| 344/363 [00:15<00:01, 15.96it/s] Loading 0: 96%|█████████▌| 349/363 [00:15<00:00, 18.93it/s] Loading 0: 98%|█████████▊| 355/363 [00:16<00:00, 23.92it/s] Loading 0: 99%|█████████▉| 360/363 [00:16<00:00, 26.52it/s]
Job cgato-nemo-12b-thespice-1853-v3-mkmlizer completed after 187.12s with status: succeeded
Stopping job with name cgato-nemo-12b-thespice-1853-v3-mkmlizer
Pipeline stage MKMLizer completed in 187.66s
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-thespice-1853-v3
Waiting for inference service cgato-nemo-12b-thespice-1853-v3 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
Failed to get response for submission zonemercy-lexical-nemov8_5966_v2: ('http://zonemercy-lexical-nemov8-5966-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission zonemercy-lexical-nemov8_5966_v2: ('http://zonemercy-lexical-nemov8-5966-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service cgato-nemo-12b-thespice-1853-v3 ready after 190.7532856464386s
Pipeline stage MKMLDeployer completed in 191.38s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.140810489654541s
Received healthy response to inference request in 2.1172025203704834s
Received healthy response to inference request in 1.9561095237731934s
Received healthy response to inference request in 1.4557485580444336s
Received healthy response to inference request in 1.5885050296783447s
5 requests
0 failed requests
5th percentile: 1.4822998523712159
10th percentile: 1.5088511466979981
20th percentile: 1.5619537353515625
30th percentile: 1.6620259284973145
40th percentile: 1.809067726135254
50th percentile: 1.9561095237731934
60th percentile: 2.020546722412109
70th percentile: 2.0849839210510255
80th percentile: 2.121924114227295
90th percentile: 2.131367301940918
95th percentile: 2.1360888957977293
99th percentile: 2.1398661708831788
mean time: 1.8516752243041992
Pipeline stage StressChecker completed in 10.69s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
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
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 5.67s
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 2.31s
Shutdown handler de-registered
cgato-nemo-12b-thespice-_1853_v3 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 2871.53s
Shutdown handler de-registered
cgato-nemo-12b-thespice-_1853_v3 status is now inactive due to auto deactivation removed underperforming models
cgato-nemo-12b-thespice-_1853_v3 status is now torndown due to DeploymentManager action