submission_id: hastagaras-mn-inst-12b-e_2944_v1
developer_uid: Hastagaras
best_of: 8
celo_rating: 1232.42
display_name: test
family_friendly_score: 0.5838
family_friendly_standard_error: 0.006971048127792549
formatter: {'memory_template': '[INST]system: ### Roleplay Instructions\n{memory}\n', 'prompt_template': '{prompt}[/INST]', 'bot_template': '{bot_name}: {message}</s>', 'user_template': '[INST]{user_name}: {message}[/INST]', 'response_template': '{bot_name}:', 'truncate_by_message': False}
generation_params: {'temperature': 0.95, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 60, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '\n\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: False
language_model: Hastagaras/MN-Inst-12B-Experiment-LMH-ET-19.35
latencies: [{'batch_size': 1, 'throughput': 0.6173293746794386, 'latency_mean': 1.619824186563492, 'latency_p50': 1.6254860162734985, 'latency_p90': 1.7912975549697876}, {'batch_size': 3, 'throughput': 1.1430521024687799, 'latency_mean': 2.6157147109508516, 'latency_p50': 2.6127521991729736, 'latency_p90': 2.9412045001983644}, {'batch_size': 5, 'throughput': 1.3704559925510627, 'latency_mean': 3.6223334562778473, 'latency_p50': 3.6493619680404663, 'latency_p90': 4.00793719291687}, {'batch_size': 6, 'throughput': 1.453401650434186, 'latency_mean': 4.104542990922928, 'latency_p50': 4.103540062904358, 'latency_p90': 4.587051820755005}, {'batch_size': 8, 'throughput': 1.5341080732039405, 'latency_mean': 5.169379912614822, 'latency_p50': 5.16151225566864, 'latency_p90': 5.897939658164978}, {'batch_size': 10, 'throughput': 1.5637731475013008, 'latency_mean': 6.3472673952579495, 'latency_p50': 6.3824368715286255, 'latency_p90': 7.037673664093018}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: Hastagaras/MN-Inst-12B-E
model_name: test
model_num_parameters: 12772070400.0
model_repo: Hastagaras/MN-Inst-12B-Experiment-LMH-ET-19.35
model_size: 13B
num_battles: 22084
num_wins: 10251
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 1.39
timestamp: 2024-11-25T15:05:58+00:00
us_pacific_date: 2024-11-25
win_ratio: 0.46418221336714366
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 hastagaras-mn-inst-12b-e-2944-v1-mkmlizer
Waiting for job on hastagaras-mn-inst-12b-e-2944-v1-mkmlizer to finish
hastagaras-mn-inst-12b-e-2944-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-mn-inst-12b-e-2944-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-mn-inst-12b-e-2944-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-mn-inst-12b-e-2944-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-mn-inst-12b-e-2944-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-mn-inst-12b-e-2944-v1-mkmlizer: ║ /___/ ║
hastagaras-mn-inst-12b-e-2944-v1-mkmlizer: ║ ║
hastagaras-mn-inst-12b-e-2944-v1-mkmlizer: ║ Version: 0.11.12 ║
hastagaras-mn-inst-12b-e-2944-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-mn-inst-12b-e-2944-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-mn-inst-12b-e-2944-v1-mkmlizer: ║ ║
hastagaras-mn-inst-12b-e-2944-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-mn-inst-12b-e-2944-v1-mkmlizer: ║ belonging to: ║
hastagaras-mn-inst-12b-e-2944-v1-mkmlizer: ║ ║
hastagaras-mn-inst-12b-e-2944-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-mn-inst-12b-e-2944-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-mn-inst-12b-e-2944-v1-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
hastagaras-mn-inst-12b-e-2944-v1-mkmlizer: ║ ║
hastagaras-mn-inst-12b-e-2944-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-mn-inst-12b-e-2944-v1-mkmlizer: quantized model in 39.644s
hastagaras-mn-inst-12b-e-2944-v1-mkmlizer: Processed model Hastagaras/MN-Inst-12B-Experiment-LMH-ET-19.35 in 91.627s
hastagaras-mn-inst-12b-e-2944-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-mn-inst-12b-e-2944-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-mn-inst-12b-e-2944-v1/config.json
hastagaras-mn-inst-12b-e-2944-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-mn-inst-12b-e-2944-v1/special_tokens_map.json
hastagaras-mn-inst-12b-e-2944-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-mn-inst-12b-e-2944-v1/tokenizer_config.json
hastagaras-mn-inst-12b-e-2944-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-mn-inst-12b-e-2944-v1/tokenizer.json
hastagaras-mn-inst-12b-e-2944-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-mn-inst-12b-e-2944-v1/flywheel_model.0.safetensors
hastagaras-mn-inst-12b-e-2944-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:11, 31.15it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:07, 49.89it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:08, 40.73it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:08, 39.99it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:07, 46.66it/s] Loading 0: 10%|▉ | 36/363 [00:00<00:06, 47.22it/s] Loading 0: 11%|█▏ | 41/363 [00:01<00:08, 37.95it/s] Loading 0: 13%|█▎ | 48/363 [00:01<00:07, 44.41it/s] Loading 0: 15%|█▍ | 53/363 [00:01<00:07, 42.09it/s] Loading 0: 16%|█▌ | 58/363 [00:01<00:07, 41.15it/s] Loading 0: 17%|█▋ | 63/363 [00:01<00:10, 27.45it/s] Loading 0: 18%|█▊ | 67/363 [00:01<00:10, 29.18it/s] Loading 0: 20%|█▉ | 71/363 [00:01<00:09, 30.62it/s] Loading 0: 21%|██ | 75/363 [00:02<00:09, 30.58it/s] Loading 0: 22%|██▏ | 79/363 [00:02<00:08, 32.66it/s] Loading 0: 23%|██▎ | 83/363 [00:02<00:09, 29.50it/s] Loading 0: 24%|██▍ | 87/363 [00:02<00:08, 31.00it/s] Loading 0: 25%|██▌ | 91/363 [00:02<00:09, 30.12it/s] Loading 0: 26%|██▋ | 96/363 [00:02<00:07, 34.67it/s] Loading 0: 28%|██▊ | 100/363 [00:02<00:08, 31.60it/s] Loading 0: 29%|██▉ | 105/363 [00:02<00:07, 35.40it/s] Loading 0: 30%|███ | 110/363 [00:03<00:06, 37.09it/s] Loading 0: 31%|███▏ | 114/363 [00:03<00:07, 34.64it/s] Loading 0: 33%|███▎ | 118/363 [00:03<00:07, 31.44it/s] Loading 0: 34%|███▍ | 125/363 [00:03<00:06, 38.43it/s] Loading 0: 36%|███▌ | 129/363 [00:03<00:06, 36.18it/s] Loading 0: 37%|███▋ | 133/363 [00:03<00:06, 36.69it/s] Loading 0: 38%|███▊ | 137/363 [00:03<00:06, 32.99it/s] Loading 0: 39%|███▉ | 141/363 [00:03<00:06, 34.26it/s] Loading 0: 40%|███▉ | 145/363 [00:04<00:09, 23.03it/s] Loading 0: 41%|████ | 149/363 [00:04<00:08, 24.01it/s] Loading 0: 43%|████▎ | 155/363 [00:04<00:06, 31.17it/s] Loading 0: 44%|████▍ | 159/363 [00:04<00:06, 29.66it/s] Loading 0: 45%|████▌ | 165/363 [00:04<00:05, 34.73it/s] Loading 0: 47%|████▋ | 169/363 [00:04<00:05, 34.24it/s] Loading 0: 48%|████▊ | 174/363 [00:05<00:05, 36.86it/s] Loading 0: 49%|████▉ | 178/363 [00:05<00:05, 35.06it/s] Loading 0: 50%|█████ | 183/363 [00:05<00:04, 36.90it/s] Loading 0: 52%|█████▏ | 187/363 [00:05<00:04, 35.61it/s] Loading 0: 53%|█████▎ | 192/363 [00:05<00:04, 36.95it/s] Loading 0: 54%|█████▍ | 196/363 [00:05<00:04, 34.63it/s] Loading 0: 55%|█████▌ | 201/363 [00:05<00:04, 36.60it/s] Loading 0: 56%|█████▋ | 205/363 [00:05<00:04, 35.36it/s] Loading 0: 58%|█████▊ | 210/363 [00:06<00:04, 37.92it/s] Loading 0: 59%|█████▉ | 214/363 [00:06<00:04, 35.66it/s] Loading 0: 60%|██████ | 218/363 [00:06<00:04, 35.23it/s] Loading 0: 61%|██████▏ | 223/363 [00:06<00:05, 27.77it/s] Loading 0: 63%|██████▎ | 227/363 [00:06<00:04, 28.86it/s] Loading 0: 64%|██████▎ | 231/363 [00:06<00:04, 29.29it/s] Loading 0: 66%|██████▌ | 238/363 [00:06<00:03, 36.84it/s] Loading 0: 67%|██████▋ | 243/363 [00:07<00:03, 39.46it/s] Loading 0: 68%|██████▊ | 248/363 [00:07<00:03, 33.39it/s] Loading 0: 70%|███████ | 255/363 [00:07<00:02, 41.36it/s] Loading 0: 72%|███████▏ | 260/363 [00:07<00:02, 41.62it/s] Loading 0: 73%|███████▎ | 265/363 [00:07<00:02, 41.57it/s] Loading 0: 74%|███████▍ | 270/363 [00:07<00:02, 43.17it/s] Loading 0: 76%|███████▌ | 275/363 [00:07<00:02, 38.10it/s] Loading 0: 78%|███████▊ | 283/363 [00:07<00:01, 46.36it/s] Loading 0: 79%|███████▉ | 288/363 [00:08<00:01, 44.05it/s] Loading 0: 81%|████████ | 293/363 [00:08<00:01, 35.59it/s] Loading 0: 82%|████████▏ | 299/363 [00:08<00:01, 39.64it/s] Loading 0: 84%|████████▎ | 304/363 [00:15<00:23, 2.48it/s] Loading 0: 85%|████████▍ | 308/363 [00:15<00:17, 3.19it/s] Loading 0: 86%|████████▌ | 312/363 [00:15<00:12, 4.12it/s] Loading 0: 88%|████████▊ | 319/363 [00:15<00:06, 6.50it/s] Loading 0: 89%|████████▉ | 324/363 [00:15<00:04, 8.54it/s] Loading 0: 91%|█████████ | 329/363 [00:16<00:03, 11.09it/s] Loading 0: 92%|█████████▏| 334/363 [00:16<00:02, 14.17it/s] Loading 0: 93%|█████████▎| 339/363 [00:16<00:01, 16.30it/s] Loading 0: 96%|█████████▌| 347/363 [00:16<00:00, 23.47it/s] Loading 0: 97%|█████████▋| 352/363 [00:16<00:00, 26.98it/s] Loading 0: 98%|█████████▊| 357/363 [00:16<00:00, 25.85it/s]
Job hastagaras-mn-inst-12b-e-2944-v1-mkmlizer completed after 124.32s with status: succeeded
Stopping job with name hastagaras-mn-inst-12b-e-2944-v1-mkmlizer
Pipeline stage MKMLizer completed in 124.84s
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 hastagaras-mn-inst-12b-e-2944-v1
Waiting for inference service hastagaras-mn-inst-12b-e-2944-v1 to be ready
Inference service hastagaras-mn-inst-12b-e-2944-v1 ready after 120.45647096633911s
Pipeline stage MKMLDeployer completed in 121.00s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.7031633853912354s
Received healthy response to inference request in 1.9745714664459229s
Received healthy response to inference request in 1.6265895366668701s
Received healthy response to inference request in 1.7038304805755615s
Received healthy response to inference request in 1.8143959045410156s
5 requests
0 failed requests
5th percentile: 1.6420377254486085
10th percentile: 1.6574859142303466
20th percentile: 1.6883822917938232
30th percentile: 1.7259435653686523
40th percentile: 1.770169734954834
50th percentile: 1.8143959045410156
60th percentile: 1.8784661293029785
70th percentile: 1.9425363540649414
80th percentile: 2.1202898502349856
90th percentile: 2.4117266178131103
95th percentile: 2.5574450016021726
99th percentile: 2.674019708633423
mean time: 1.964510154724121
Pipeline stage StressChecker completed in 11.18s
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 2.32s
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 2.27s
Shutdown handler de-registered
hastagaras-mn-inst-12b-e_2944_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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service hastagaras-mn-inst-12b-e-2944-v1-profiler
Waiting for inference service hastagaras-mn-inst-12b-e-2944-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 2977.47s
Shutdown handler de-registered
hastagaras-mn-inst-12b-e_2944_v1 status is now inactive due to auto deactivation removed underperforming models