developer_uid: azuruce
submission_id: chaiml-nemo-espresso-an_5543_v14
model_name: chaiml-nemo-espresso-an_5543_v14
model_group: ChaiML/nemo_espresso_ant
status: inactive
timestamp: 2024-12-07T06:43:25+00:00
num_battles: 12511
num_wins: 6421
celo_rating: 1272.91
family_friendly_score: 0.5858
family_friendly_standard_error: 0.006966180589103328
submission_type: basic
model_repo: ChaiML/nemo_espresso_ant_llama_story_241205_albert_v1_sft-3e128a
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.642275268665546, 'latency_mean': 1.5569044768810272, 'latency_p50': 1.5508650541305542, 'latency_p90': 1.7108229160308837}, {'batch_size': 4, 'throughput': 1.4810843309503035, 'latency_mean': 2.685578134059906, 'latency_p50': 2.6881062984466553, 'latency_p90': 3.0810626983642577}, {'batch_size': 5, 'throughput': 1.6210104708681743, 'latency_mean': 3.067678154706955, 'latency_p50': 3.052843689918518, 'latency_p90': 3.4985184907913207}, {'batch_size': 8, 'throughput': 1.888602502122385, 'latency_mean': 4.204372453689575, 'latency_p50': 4.211190342903137, 'latency_p90': 4.70952033996582}, {'batch_size': 10, 'throughput': 1.9973275037756528, 'latency_mean': 4.972389686107635, 'latency_p50': 4.952517032623291, 'latency_p90': 5.61308102607727}, {'batch_size': 12, 'throughput': 2.0442852053785887, 'latency_mean': 5.82006551027298, 'latency_p50': 5.8242127895355225, 'latency_p90': 6.594366264343262}, {'batch_size': 15, 'throughput': 2.0767466300500486, 'latency_mean': 7.15086282491684, 'latency_p50': 7.169666528701782, 'latency_p90': 8.240034222602844}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-nemo-espresso-an_5543_v14
is_internal_developer: True
language_model: ChaiML/nemo_espresso_ant_llama_story_241205_albert_v1_sft-3e128a
model_size: 13B
ranking_group: single
throughput_3p7s: 1.8
us_pacific_date: 2024-12-06
win_ratio: 0.5132283590440413
generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '####', 'Bot:', 'User:', 'You:', '<|im_end|>', '<|eot_id|>'], 'max_input_tokens': 1024, 'best_of': 4, '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-an-5543-v14-mkmlizer
Waiting for job on chaiml-nemo-espresso-an-5543-v14-mkmlizer to finish
chaiml-nemo-espresso-an-5543-v14-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-espresso-an-5543-v14-mkmlizer: ║ _____ __ __ ║
chaiml-nemo-espresso-an-5543-v14-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-nemo-espresso-an-5543-v14-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-nemo-espresso-an-5543-v14-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-nemo-espresso-an-5543-v14-mkmlizer: ║ /___/ ║
chaiml-nemo-espresso-an-5543-v14-mkmlizer: ║ ║
chaiml-nemo-espresso-an-5543-v14-mkmlizer: ║ Version: 0.11.12 ║
chaiml-nemo-espresso-an-5543-v14-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-nemo-espresso-an-5543-v14-mkmlizer: ║ https://mk1.ai ║
chaiml-nemo-espresso-an-5543-v14-mkmlizer: ║ ║
chaiml-nemo-espresso-an-5543-v14-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-nemo-espresso-an-5543-v14-mkmlizer: ║ belonging to: ║
chaiml-nemo-espresso-an-5543-v14-mkmlizer: ║ ║
chaiml-nemo-espresso-an-5543-v14-mkmlizer: ║ Chai Research Corp. ║
chaiml-nemo-espresso-an-5543-v14-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-nemo-espresso-an-5543-v14-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
chaiml-nemo-espresso-an-5543-v14-mkmlizer: ║ ║
chaiml-nemo-espresso-an-5543-v14-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-espresso-an-5543-v14-mkmlizer: Downloaded to shared memory in 30.764s
chaiml-nemo-espresso-an-5543-v14-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpbvkloqgt, device:0
chaiml-nemo-espresso-an-5543-v14-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-espresso-an-5543-v14-mkmlizer: quantized model in 37.301s
chaiml-nemo-espresso-an-5543-v14-mkmlizer: Processed model ChaiML/nemo_espresso_ant_llama_story_241205_albert_v1_sft-3e128a in 68.066s
chaiml-nemo-espresso-an-5543-v14-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-espresso-an-5543-v14-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-espresso-an-5543-v14-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-espresso-an-5543-v14
chaiml-nemo-espresso-an-5543-v14-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-espresso-an-5543-v14/config.json
chaiml-nemo-espresso-an-5543-v14-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-espresso-an-5543-v14/special_tokens_map.json
chaiml-nemo-espresso-an-5543-v14-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-espresso-an-5543-v14/tokenizer_config.json
chaiml-nemo-espresso-an-5543-v14-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-espresso-an-5543-v14/tokenizer.json
chaiml-nemo-espresso-an-5543-v14-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-espresso-an-5543-v14/flywheel_model.0.safetensors
chaiml-nemo-espresso-an-5543-v14-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:12, 28.00it/s] Loading 0: 3%|▎ | 12/363 [00:00<00:07, 44.46it/s] Loading 0: 5%|▍ | 17/363 [00:00<00:08, 42.69it/s] Loading 0: 6%|▌ | 22/363 [00:00<00:07, 43.44it/s] Loading 0: 8%|▊ | 28/363 [00:00<00:08, 41.87it/s] Loading 0: 9%|▉ | 33/363 [00:00<00:07, 41.68it/s] Loading 0: 11%|█ | 40/363 [00:00<00:06, 47.80it/s] Loading 0: 12%|█▏ | 45/363 [00:01<00:06, 48.04it/s] Loading 0: 14%|█▍ | 50/363 [00:01<00:08, 37.87it/s] Loading 0: 15%|█▌ | 56/363 [00:01<00:07, 42.15it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:09, 32.55it/s] Loading 0: 18%|█▊ | 65/363 [00:01<00:09, 31.22it/s] Loading 0: 20%|█▉ | 71/363 [00:01<00:08, 36.18it/s] Loading 0: 21%|██ | 75/363 [00:01<00:08, 35.21it/s] Loading 0: 22%|██▏ | 80/363 [00:02<00:07, 38.27it/s] Loading 0: 23%|██▎ | 85/363 [00:02<00:07, 37.50it/s] Loading 0: 25%|██▍ | 89/363 [00:02<00:07, 37.99it/s] Loading 0: 26%|██▌ | 93/363 [00:02<00:07, 36.82it/s] Loading 0: 27%|██▋ | 98/363 [00:02<00:06, 38.96it/s] Loading 0: 28%|██▊ | 102/363 [00:02<00:07, 37.03it/s] Loading 0: 29%|██▉ | 106/363 [00:02<00:06, 37.10it/s] Loading 0: 31%|███ | 112/363 [00:02<00:05, 42.77it/s] Loading 0: 32%|███▏ | 117/363 [00:02<00:05, 41.35it/s] Loading 0: 34%|███▍ | 123/363 [00:03<00:05, 40.28it/s] Loading 0: 35%|███▌ | 128/363 [00:03<00:06, 38.75it/s] Loading 0: 37%|███▋ | 134/363 [00:03<00:05, 43.66it/s] Loading 0: 38%|███▊ | 139/363 [00:03<00:05, 43.76it/s] Loading 0: 40%|███▉ | 144/363 [00:03<00:07, 27.54it/s] Loading 0: 41%|████ | 149/363 [00:03<00:07, 29.82it/s] Loading 0: 43%|████▎ | 157/363 [00:04<00:05, 38.71it/s] Loading 0: 45%|████▍ | 163/363 [00:04<00:05, 39.09it/s] Loading 0: 46%|████▋ | 168/363 [00:04<00:05, 37.39it/s] Loading 0: 48%|████▊ | 174/363 [00:04<00:04, 42.20it/s] Loading 0: 49%|████▉ | 179/363 [00:04<00:04, 41.75it/s] Loading 0: 51%|█████ | 184/363 [00:04<00:04, 41.95it/s] Loading 0: 52%|█████▏ | 189/363 [00:04<00:03, 43.67it/s] Loading 0: 53%|█████▎ | 194/363 [00:05<00:04, 36.94it/s] Loading 0: 55%|█████▌ | 201/363 [00:05<00:03, 44.62it/s] Loading 0: 57%|█████▋ | 206/363 [00:05<00:03, 44.59it/s] Loading 0: 58%|█████▊ | 211/363 [00:05<00:03, 45.48it/s] Loading 0: 60%|█████▉ | 216/363 [00:05<00:03, 46.21it/s] Loading 0: 61%|██████ | 222/363 [00:05<00:03, 43.24it/s] Loading 0: 63%|██████▎ | 227/363 [00:05<00:04, 31.53it/s] Loading 0: 64%|██████▎ | 231/363 [00:06<00:04, 30.84it/s] Loading 0: 66%|██████▌ | 238/363 [00:06<00:03, 37.87it/s] Loading 0: 67%|██████▋ | 244/363 [00:06<00:03, 38.18it/s] Loading 0: 69%|██████▊ | 249/363 [00:06<00:02, 38.91it/s] Loading 0: 71%|███████ | 256/363 [00:06<00:02, 43.91it/s] Loading 0: 72%|███████▏ | 262/363 [00:06<00:02, 42.85it/s] Loading 0: 74%|███████▎ | 267/363 [00:06<00:02, 42.72it/s] Loading 0: 75%|███████▌ | 274/363 [00:06<00:01, 47.08it/s] Loading 0: 77%|███████▋ | 280/363 [00:07<00:01, 44.25it/s] Loading 0: 79%|███████▊ | 285/363 [00:07<00:01, 43.40it/s] Loading 0: 80%|████████ | 292/363 [00:07<00:01, 47.28it/s] Loading 0: 82%|████████▏ | 298/363 [00:07<00:01, 44.24it/s] Loading 0: 84%|████████▎ | 304/363 [00:14<00:20, 2.83it/s] Loading 0: 85%|████████▍ | 308/363 [00:14<00:15, 3.55it/s] Loading 0: 86%|████████▌ | 312/363 [00:14<00:11, 4.52it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:05, 7.30it/s] Loading 0: 90%|████████▉ | 326/363 [00:14<00:03, 9.70it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:02, 12.17it/s] Loading 0: 93%|█████████▎| 338/363 [00:15<00:01, 16.90it/s] Loading 0: 95%|█████████▍| 344/363 [00:15<00:00, 20.35it/s] Loading 0: 96%|█████████▌| 349/363 [00:15<00:00, 23.37it/s] Loading 0: 98%|█████████▊| 356/363 [00:15<00:00, 29.54it/s] Loading 0: 99%|█████████▉| 361/363 [00:15<00:00, 32.78it/s]
Job chaiml-nemo-espresso-an-5543-v14-mkmlizer completed after 93.86s with status: succeeded
Stopping job with name chaiml-nemo-espresso-an-5543-v14-mkmlizer
Pipeline stage MKMLizer completed in 94.37s
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 chaiml-nemo-espresso-an-5543-v14
Waiting for inference service chaiml-nemo-espresso-an-5543-v14 to be ready
Inference service chaiml-nemo-espresso-an-5543-v14 ready after 170.59010410308838s
Pipeline stage MKMLDeployer completed in 171.62s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9672327041625977s
Received healthy response to inference request in 1.539430856704712s
Received healthy response to inference request in 1.8762874603271484s
Received healthy response to inference request in 1.4360270500183105s
Received healthy response to inference request in 1.664966344833374s
5 requests
0 failed requests
5th percentile: 1.456707811355591
10th percentile: 1.477388572692871
20th percentile: 1.5187500953674316
30th percentile: 1.5645379543304443
40th percentile: 1.6147521495819093
50th percentile: 1.664966344833374
60th percentile: 1.7494947910308838
70th percentile: 1.8340232372283936
80th percentile: 1.8944765090942384
90th percentile: 1.930854606628418
95th percentile: 1.9490436553955077
99th percentile: 1.9635948944091797
mean time: 1.6967888832092286
Pipeline stage StressChecker completed in 9.91s
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 2.03s
Shutdown handler de-registered
chaiml-nemo-espresso-an_5543_v14 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 0.11s
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-an-5543-v14-profiler
Waiting for inference service chaiml-nemo-espresso-an-5543-v14-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 2489.65s
Shutdown handler de-registered
chaiml-nemo-espresso-an_5543_v14 status is now inactive due to auto deactivation removed underperforming models