developer_uid: azuruce
submission_id: chaiml-nemo-espresso-ant_1376_v3
model_name: chaiml-nemo-espresso-ant_1376_v3
model_group: ChaiML/nemo_espresso_ant
status: torndown
timestamp: 2024-12-06T22:42:43+00:00
num_battles: 6343
num_wins: 3433
celo_rating: 1277.63
family_friendly_score: 0.5660000000000001
family_friendly_standard_error: 0.007009193962218481
submission_type: basic
model_repo: ChaiML/nemo_espresso_ant_llama_story_241205_albert_ez_v1_sft-3e128a
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6014548725349912, 'latency_mean': 1.6625501525402069, 'latency_p50': 1.6595348119735718, 'latency_p90': 1.83895583152771}, {'batch_size': 3, 'throughput': 1.114064095156872, 'latency_mean': 2.685374253988266, 'latency_p50': 2.67019522190094, 'latency_p90': 2.9774140119552612}, {'batch_size': 5, 'throughput': 1.3682128870023142, 'latency_mean': 3.632858324050903, 'latency_p50': 3.606789231300354, 'latency_p90': 4.156325006484986}, {'batch_size': 6, 'throughput': 1.4151797962318824, 'latency_mean': 4.214197078943252, 'latency_p50': 4.2208380699157715, 'latency_p90': 4.6793503046035765}, {'batch_size': 8, 'throughput': 1.4917627304327175, 'latency_mean': 5.343809642791748, 'latency_p50': 5.368115067481995, 'latency_p90': 6.012186741828918}, {'batch_size': 10, 'throughput': 1.5377688001662313, 'latency_mean': 6.456657098531723, 'latency_p50': 6.482059359550476, 'latency_p90': 7.33192617893219}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-nemo-espresso-ant_1376_v3
is_internal_developer: True
language_model: ChaiML/nemo_espresso_ant_llama_story_241205_albert_ez_v1_sft-3e128a
model_size: 13B
ranking_group: single
throughput_3p7s: 1.38
us_pacific_date: 2024-12-06
win_ratio: 0.5412265489516002
generation_params: {'temperature': 0.8, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>', '<|end_of_text|>', 'You:'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
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 chaiml-nemo-espresso-ant-1376-v3-mkmlizer
Waiting for job on chaiml-nemo-espresso-ant-1376-v3-mkmlizer to finish
chaiml-nemo-espresso-ant-1376-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-espresso-ant-1376-v3-mkmlizer: ║ _____ __ __ ║
chaiml-nemo-espresso-ant-1376-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-nemo-espresso-ant-1376-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-nemo-espresso-ant-1376-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-nemo-espresso-ant-1376-v3-mkmlizer: ║ /___/ ║
chaiml-nemo-espresso-ant-1376-v3-mkmlizer: ║ ║
chaiml-nemo-espresso-ant-1376-v3-mkmlizer: ║ Version: 0.11.12 ║
chaiml-nemo-espresso-ant-1376-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-nemo-espresso-ant-1376-v3-mkmlizer: ║ https://mk1.ai ║
chaiml-nemo-espresso-ant-1376-v3-mkmlizer: ║ ║
chaiml-nemo-espresso-ant-1376-v3-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-nemo-espresso-ant-1376-v3-mkmlizer: ║ belonging to: ║
chaiml-nemo-espresso-ant-1376-v3-mkmlizer: ║ ║
chaiml-nemo-espresso-ant-1376-v3-mkmlizer: ║ Chai Research Corp. ║
chaiml-nemo-espresso-ant-1376-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-nemo-espresso-ant-1376-v3-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
chaiml-nemo-espresso-ant-1376-v3-mkmlizer: ║ ║
chaiml-nemo-espresso-ant-1376-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-espresso-ant-1376-v3-mkmlizer: Downloaded to shared memory in 31.947s
chaiml-nemo-espresso-ant-1376-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpl4itsitl, device:0
chaiml-nemo-espresso-ant-1376-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-espresso-ant-1376-v3-mkmlizer: quantized model in 38.139s
chaiml-nemo-espresso-ant-1376-v3-mkmlizer: Processed model ChaiML/nemo_espresso_ant_llama_story_241205_albert_ez_v1_sft-3e128a in 70.086s
chaiml-nemo-espresso-ant-1376-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-espresso-ant-1376-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-espresso-ant-1376-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-espresso-ant-1376-v3
chaiml-nemo-espresso-ant-1376-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-espresso-ant-1376-v3/config.json
chaiml-nemo-espresso-ant-1376-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-espresso-ant-1376-v3/special_tokens_map.json
chaiml-nemo-espresso-ant-1376-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-espresso-ant-1376-v3/tokenizer_config.json
chaiml-nemo-espresso-ant-1376-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-espresso-ant-1376-v3/tokenizer.json
chaiml-nemo-espresso-ant-1376-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-espresso-ant-1376-v3/flywheel_model.0.safetensors
chaiml-nemo-espresso-ant-1376-v3-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:14, 24.38it/s] Loading 0: 3%|▎ | 12/363 [00:00<00:08, 39.77it/s] Loading 0: 5%|▍ | 17/363 [00:00<00:09, 37.19it/s] Loading 0: 6%|▌ | 21/363 [00:00<00:09, 34.41it/s] Loading 0: 7%|▋ | 25/363 [00:00<00:10, 32.32it/s] Loading 0: 8%|▊ | 30/363 [00:00<00:09, 36.22it/s] Loading 0: 9%|▉ | 34/363 [00:00<00:09, 36.35it/s] Loading 0: 11%|█ | 39/363 [00:01<00:08, 38.31it/s] Loading 0: 12%|█▏ | 43/363 [00:01<00:09, 35.54it/s] Loading 0: 13%|█▎ | 48/363 [00:01<00:08, 37.40it/s] Loading 0: 14%|█▍ | 52/363 [00:01<00:09, 34.32it/s] Loading 0: 15%|█▌ | 56/363 [00:01<00:09, 33.05it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:13, 22.30it/s] Loading 0: 18%|█▊ | 64/363 [00:02<00:13, 22.06it/s] Loading 0: 20%|█▉ | 72/363 [00:02<00:09, 31.71it/s] Loading 0: 21%|██▏ | 78/363 [00:02<00:08, 34.56it/s] Loading 0: 23%|██▎ | 82/363 [00:02<00:08, 34.33it/s] Loading 0: 25%|██▍ | 90/363 [00:02<00:06, 42.80it/s] Loading 0: 26%|██▋ | 96/363 [00:02<00:06, 42.19it/s] Loading 0: 28%|██▊ | 101/363 [00:02<00:06, 41.16it/s] Loading 0: 29%|██▉ | 107/363 [00:02<00:05, 45.53it/s] Loading 0: 31%|███ | 112/363 [00:03<00:05, 46.57it/s] Loading 0: 32%|███▏ | 117/363 [00:03<00:06, 40.36it/s] Loading 0: 34%|███▎ | 122/363 [00:03<00:06, 39.03it/s] Loading 0: 35%|███▍ | 127/363 [00:03<00:07, 30.47it/s] Loading 0: 37%|███▋ | 134/363 [00:03<00:06, 37.37it/s] Loading 0: 38%|███▊ | 139/363 [00:03<00:05, 37.40it/s] Loading 0: 40%|███▉ | 144/363 [00:04<00:09, 22.30it/s] Loading 0: 41%|████ | 149/363 [00:04<00:08, 24.16it/s] Loading 0: 43%|████▎ | 156/363 [00:04<00:06, 31.08it/s] Loading 0: 44%|████▍ | 161/363 [00:04<00:06, 32.20it/s] Loading 0: 45%|████▌ | 165/363 [00:04<00:05, 33.11it/s] Loading 0: 47%|████▋ | 169/363 [00:05<00:06, 32.23it/s] Loading 0: 48%|████▊ | 173/363 [00:05<00:05, 33.49it/s] Loading 0: 49%|████▉ | 177/363 [00:05<00:06, 29.65it/s] Loading 0: 50%|████▉ | 181/363 [00:05<00:05, 31.93it/s] Loading 0: 51%|█████ | 185/363 [00:05<00:06, 29.36it/s] Loading 0: 53%|█████▎ | 192/363 [00:05<00:04, 37.47it/s] Loading 0: 54%|█████▍ | 197/363 [00:05<00:04, 36.61it/s] Loading 0: 55%|█████▌ | 201/363 [00:05<00:04, 36.16it/s] Loading 0: 56%|█████▋ | 205/363 [00:06<00:04, 34.72it/s] Loading 0: 58%|█████▊ | 209/363 [00:06<00:04, 34.77it/s] Loading 0: 59%|█████▊ | 213/363 [00:06<00:04, 30.53it/s] Loading 0: 60%|██████ | 218/363 [00:06<00:04, 32.89it/s] Loading 0: 61%|██████▏ | 223/363 [00:06<00:05, 24.81it/s] Loading 0: 62%|██████▏ | 226/363 [00:06<00:05, 24.60it/s] Loading 0: 63%|██████▎ | 230/363 [00:07<00:05, 24.00it/s] Loading 0: 65%|██████▍ | 235/363 [00:07<00:04, 28.39it/s] Loading 0: 66%|██████▌ | 239/363 [00:07<00:04, 27.52it/s] Loading 0: 67%|██████▋ | 244/363 [00:07<00:03, 32.34it/s] Loading 0: 68%|██████▊ | 248/363 [00:07<00:03, 31.05it/s] Loading 0: 70%|███████ | 255/363 [00:07<00:02, 40.19it/s] Loading 0: 72%|███████▏ | 260/363 [00:07<00:02, 41.56it/s] Loading 0: 73%|███████▎ | 265/363 [00:07<00:02, 43.47it/s] Loading 0: 75%|███████▍ | 271/363 [00:08<00:02, 42.31it/s] Loading 0: 76%|███████▌ | 276/363 [00:08<00:02, 39.87it/s] Loading 0: 78%|███████▊ | 283/363 [00:08<00:01, 45.54it/s] Loading 0: 79%|███████▉ | 288/363 [00:08<00:01, 46.21it/s] Loading 0: 81%|████████ | 293/363 [00:08<00:01, 38.36it/s] Loading 0: 82%|████████▏ | 299/363 [00:08<00:01, 43.40it/s] Loading 0: 84%|████████▎ | 304/363 [00:15<00:23, 2.51it/s] Loading 0: 85%|████████▍ | 308/363 [00:15<00:17, 3.22it/s] Loading 0: 86%|████████▌ | 312/363 [00:15<00:12, 4.17it/s] Loading 0: 88%|████████▊ | 319/363 [00:15<00:06, 6.58it/s] Loading 0: 89%|████████▉ | 324/363 [00:16<00:04, 8.64it/s] Loading 0: 91%|█████████ | 329/363 [00:16<00:03, 11.26it/s] Loading 0: 92%|█████████▏| 334/363 [00:16<00:02, 14.47it/s] Loading 0: 93%|█████████▎| 339/363 [00:16<00:01, 16.43it/s] Loading 0: 95%|█████████▌| 346/363 [00:16<00:00, 22.53it/s] Loading 0: 97%|█████████▋| 351/363 [00:16<00:00, 25.00it/s] Loading 0: 98%|█████████▊| 356/363 [00:16<00:00, 27.42it/s] Loading 0: 99%|█████████▉| 361/363 [00:17<00:00, 30.73it/s]
Job chaiml-nemo-espresso-ant-1376-v3-mkmlizer completed after 94.84s with status: succeeded
Stopping job with name chaiml-nemo-espresso-ant-1376-v3-mkmlizer
Pipeline stage MKMLizer completed in 95.43s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nemo-espresso-ant-1376-v3
Waiting for inference service chaiml-nemo-espresso-ant-1376-v3 to be ready
Inference service chaiml-nemo-espresso-ant-1376-v3 ready after 160.60484766960144s
Pipeline stage MKMLDeployer completed in 161.12s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0306215286254883s
Received healthy response to inference request in 1.674041748046875s
Received healthy response to inference request in 1.9670393466949463s
Received healthy response to inference request in 1.4130449295043945s
Received healthy response to inference request in 1.6409521102905273s
5 requests
0 failed requests
5th percentile: 1.4586263656616212
10th percentile: 1.5042078018188476
20th percentile: 1.5953706741333007
30th percentile: 1.6475700378417968
40th percentile: 1.660805892944336
50th percentile: 1.674041748046875
60th percentile: 1.7912407875061036
70th percentile: 1.908439826965332
80th percentile: 1.9797557830810546
90th percentile: 2.0051886558532717
95th percentile: 2.01790509223938
99th percentile: 2.0280782413482665
mean time: 1.7451399326324464
Pipeline stage StressChecker completed in 10.12s
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 2.83s
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 2.29s
Shutdown handler de-registered
chaiml-nemo-espresso-ant_1376_v3 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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-nemo-espresso-ant-1376-v3-profiler
Waiting for inference service chaiml-nemo-espresso-ant-1376-v3-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 2541.86s
Shutdown handler de-registered
chaiml-nemo-espresso-ant_1376_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-nemo-espresso-ant_1376_v3 status is now torndown due to DeploymentManager action
chaiml-nemo-espresso-ant_1376_v3 status is now torndown due to DeploymentManager action
chaiml-nemo-espresso-ant_1376_v3 status is now torndown due to DeploymentManager action