developer_uid: azuruce
submission_id: chaiml-nemo-espresso-ant_1376_v1
model_name: chaiml-nemo-espresso-ant_1376_v1
model_group: ChaiML/nemo_espresso_ant
status: inactive
timestamp: 2024-12-06T22:41:43+00:00
num_battles: 6435
num_wins: 3417
celo_rating: 1272.63
family_friendly_score: 0.5674
family_friendly_standard_error: 0.007006528955196004
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': 0.604793445845417, 'latency_mean': 1.6533914589881897, 'latency_p50': 1.6644792556762695, 'latency_p90': 1.8030502319335937}, {'batch_size': 3, 'throughput': 1.1103795097654916, 'latency_mean': 2.6958941447734834, 'latency_p50': 2.6940125226974487, 'latency_p90': 2.9495357275009155}, {'batch_size': 5, 'throughput': 1.3447583920447834, 'latency_mean': 3.7111377608776093, 'latency_p50': 3.712465524673462, 'latency_p90': 4.140910387039185}, {'batch_size': 6, 'throughput': 1.407436382676987, 'latency_mean': 4.243293979167938, 'latency_p50': 4.257080554962158, 'latency_p90': 4.767031192779541}, {'batch_size': 8, 'throughput': 1.491234836782622, 'latency_mean': 5.333828109502792, 'latency_p50': 5.340576171875, 'latency_p90': 5.987790107727051}, {'batch_size': 10, 'throughput': 1.5099751615208914, 'latency_mean': 6.565188459157944, 'latency_p50': 6.564110040664673, 'latency_p90': 7.354935646057129}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-nemo-espresso-ant_1376_v1
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: 1.35
us_pacific_date: 2024-12-06
win_ratio: 0.531002331002331
generation_params: {'temperature': 1.0, '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': '{memory}\n', 'prompt_template': '{prompt}\n', '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-v1-mkmlizer
Waiting for job on chaiml-nemo-espresso-ant-1376-v1-mkmlizer to finish
chaiml-nemo-espresso-ant-1376-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-espresso-ant-1376-v1-mkmlizer: ║ _____ __ __ ║
chaiml-nemo-espresso-ant-1376-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-nemo-espresso-ant-1376-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-nemo-espresso-ant-1376-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-nemo-espresso-ant-1376-v1-mkmlizer: ║ /___/ ║
chaiml-nemo-espresso-ant-1376-v1-mkmlizer: ║ ║
chaiml-nemo-espresso-ant-1376-v1-mkmlizer: ║ Version: 0.11.12 ║
chaiml-nemo-espresso-ant-1376-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-nemo-espresso-ant-1376-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-nemo-espresso-ant-1376-v1-mkmlizer: ║ ║
chaiml-nemo-espresso-ant-1376-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-nemo-espresso-ant-1376-v1-mkmlizer: ║ belonging to: ║
chaiml-nemo-espresso-ant-1376-v1-mkmlizer: ║ ║
chaiml-nemo-espresso-ant-1376-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-nemo-espresso-ant-1376-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-nemo-espresso-ant-1376-v1-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
chaiml-nemo-espresso-ant-1376-v1-mkmlizer: ║ ║
chaiml-nemo-espresso-ant-1376-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-espresso-ant-1376-v1-mkmlizer: Downloaded to shared memory in 48.702s
chaiml-nemo-espresso-ant-1376-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp7ywklt9k, device:0
chaiml-nemo-espresso-ant-1376-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-espresso-ant-1376-v1-mkmlizer: quantized model in 37.698s
chaiml-nemo-espresso-ant-1376-v1-mkmlizer: Processed model ChaiML/nemo_espresso_ant_llama_story_241205_albert_ez_v1_sft-3e128a in 86.400s
chaiml-nemo-espresso-ant-1376-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-espresso-ant-1376-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-espresso-ant-1376-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-espresso-ant-1376-v1
chaiml-nemo-espresso-ant-1376-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-espresso-ant-1376-v1/config.json
chaiml-nemo-espresso-ant-1376-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-espresso-ant-1376-v1/special_tokens_map.json
chaiml-nemo-espresso-ant-1376-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-espresso-ant-1376-v1/tokenizer_config.json
chaiml-nemo-espresso-ant-1376-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-espresso-ant-1376-v1/tokenizer.json
chaiml-nemo-espresso-ant-1376-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-espresso-ant-1376-v1/flywheel_model.0.safetensors
chaiml-nemo-espresso-ant-1376-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:15, 22.48it/s] Loading 0: 3%|▎ | 10/363 [00:00<00:11, 32.08it/s] Loading 0: 4%|▍ | 14/363 [00:00<00:12, 28.81it/s] Loading 0: 6%|▌ | 21/363 [00:00<00:08, 38.51it/s] Loading 0: 7%|▋ | 26/363 [00:00<00:09, 37.36it/s] Loading 0: 8%|▊ | 30/363 [00:00<00:09, 36.58it/s] Loading 0: 9%|▉ | 34/363 [00:00<00:09, 34.99it/s] Loading 0: 11%|█ | 39/363 [00:01<00:08, 36.93it/s] Loading 0: 12%|█▏ | 43/363 [00:01<00:09, 34.49it/s] Loading 0: 13%|█▎ | 48/363 [00:01<00:08, 36.95it/s] Loading 0: 14%|█▍ | 52/363 [00:01<00:08, 35.28it/s] Loading 0: 15%|█▌ | 56/363 [00:01<00:08, 35.17it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:11, 25.17it/s] Loading 0: 18%|█▊ | 64/363 [00:02<00:12, 23.40it/s] Loading 0: 19%|█▉ | 70/363 [00:02<00:09, 30.69it/s] Loading 0: 20%|██ | 74/363 [00:02<00:09, 29.45it/s] Loading 0: 22%|██▏ | 80/363 [00:02<00:08, 34.47it/s] Loading 0: 23%|██▎ | 84/363 [00:02<00:08, 33.66it/s] Loading 0: 25%|██▍ | 89/363 [00:02<00:07, 36.38it/s] Loading 0: 26%|██▌ | 93/363 [00:02<00:07, 34.74it/s] Loading 0: 27%|██▋ | 98/363 [00:02<00:07, 36.66it/s] Loading 0: 28%|██▊ | 102/363 [00:03<00:07, 34.39it/s] Loading 0: 29%|██▉ | 106/363 [00:03<00:07, 33.51it/s] Loading 0: 30%|███ | 110/363 [00:03<00:07, 34.95it/s] Loading 0: 31%|███▏ | 114/363 [00:03<00:07, 33.13it/s] Loading 0: 33%|███▎ | 118/363 [00:03<00:08, 30.48it/s] Loading 0: 34%|███▍ | 123/363 [00:03<00:06, 35.14it/s] Loading 0: 35%|███▍ | 127/363 [00:03<00:07, 33.16it/s] Loading 0: 37%|███▋ | 134/363 [00:03<00:05, 41.42it/s] Loading 0: 38%|███▊ | 139/363 [00:04<00:05, 42.32it/s] Loading 0: 40%|███▉ | 144/363 [00:04<00:07, 27.57it/s] Loading 0: 41%|████ | 149/363 [00:04<00:07, 30.42it/s] Loading 0: 43%|████▎ | 157/363 [00:04<00:05, 39.31it/s] Loading 0: 45%|████▍ | 163/363 [00:04<00:05, 39.87it/s] Loading 0: 46%|████▋ | 168/363 [00:04<00:04, 40.15it/s] Loading 0: 48%|████▊ | 175/363 [00:05<00:04, 45.54it/s] Loading 0: 50%|████▉ | 181/363 [00:05<00:04, 43.73it/s] Loading 0: 51%|█████ | 186/363 [00:05<00:04, 42.01it/s] Loading 0: 53%|█████▎ | 192/363 [00:05<00:03, 46.05it/s] Loading 0: 54%|█████▍ | 197/363 [00:05<00:03, 43.48it/s] Loading 0: 56%|█████▌ | 202/363 [00:05<00:04, 40.11it/s] Loading 0: 57%|█████▋ | 207/363 [00:05<00:03, 39.84it/s] Loading 0: 58%|█████▊ | 212/363 [00:06<00:04, 32.08it/s] Loading 0: 60%|█████▉ | 217/363 [00:06<00:04, 35.66it/s] Loading 0: 61%|██████ | 222/363 [00:06<00:03, 36.76it/s] Loading 0: 62%|██████▏ | 226/363 [00:06<00:05, 23.88it/s] Loading 0: 63%|██████▎ | 230/363 [00:06<00:05, 24.25it/s] Loading 0: 65%|██████▍ | 235/363 [00:06<00:04, 28.98it/s] Loading 0: 66%|██████▌ | 239/363 [00:07<00:04, 28.53it/s] Loading 0: 67%|██████▋ | 244/363 [00:07<00:03, 32.73it/s] Loading 0: 68%|██████▊ | 248/363 [00:07<00:03, 30.23it/s] Loading 0: 70%|██████▉ | 253/363 [00:07<00:03, 34.42it/s] Loading 0: 71%|███████ | 257/363 [00:07<00:03, 31.82it/s] Loading 0: 72%|███████▏ | 262/363 [00:07<00:02, 35.77it/s] Loading 0: 73%|███████▎ | 266/363 [00:07<00:03, 32.26it/s] Loading 0: 75%|███████▍ | 271/363 [00:07<00:02, 35.93it/s] Loading 0: 76%|███████▌ | 275/363 [00:08<00:02, 32.36it/s] Loading 0: 77%|███████▋ | 280/363 [00:08<00:02, 36.20it/s] Loading 0: 78%|███████▊ | 284/363 [00:08<00:02, 32.47it/s] Loading 0: 80%|███████▉ | 289/363 [00:08<00:02, 36.17it/s] Loading 0: 81%|████████ | 293/363 [00:08<00:02, 32.37it/s] Loading 0: 82%|████████▏ | 298/363 [00:08<00:01, 35.79it/s] Loading 0: 83%|████████▎ | 303/363 [00:08<00:01, 36.35it/s] Loading 0: 85%|████████▍ | 307/363 [00:15<00:26, 2.08it/s] Loading 0: 86%|████████▌ | 312/363 [00:15<00:16, 3.00it/s] Loading 0: 88%|████████▊ | 320/363 [00:15<00:08, 5.07it/s] Loading 0: 90%|████████▉ | 326/363 [00:16<00:05, 6.98it/s] Loading 0: 91%|█████████ | 331/363 [00:16<00:03, 9.03it/s] Loading 0: 93%|█████████▎| 338/363 [00:16<00:01, 12.94it/s] Loading 0: 95%|█████████▍| 344/363 [00:16<00:01, 16.25it/s] Loading 0: 96%|█████████▌| 349/363 [00:16<00:00, 19.37it/s] Loading 0: 98%|█████████▊| 356/363 [00:16<00:00, 25.31it/s] Loading 0: 100%|█████████▉| 362/363 [00:16<00:00, 28.35it/s]
Job chaiml-nemo-espresso-ant-1376-v1-mkmlizer completed after 115.81s with status: succeeded
Stopping job with name chaiml-nemo-espresso-ant-1376-v1-mkmlizer
Pipeline stage MKMLizer completed in 116.35s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.21s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nemo-espresso-ant-1376-v1
Waiting for inference service chaiml-nemo-espresso-ant-1376-v1 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
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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service chaiml-nemo-espresso-ant-1376-v1 ready after 170.93360924720764s
Pipeline stage MKMLDeployer completed in 171.59s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.7673726081848145s
Received healthy response to inference request in 2.02541184425354s
Received healthy response to inference request in 1.6442131996154785s
Received healthy response to inference request in 1.8414576053619385s
Received healthy response to inference request in 2.138685464859009s
5 requests
0 failed requests
5th percentile: 1.6836620807647704
10th percentile: 1.7231109619140625
20th percentile: 1.8020087242126466
30th percentile: 1.8782484531402588
40th percentile: 1.9518301486968994
50th percentile: 2.02541184425354
60th percentile: 2.0707212924957275
70th percentile: 2.116030740737915
80th percentile: 2.6644228935241703
90th percentile: 3.7158977508544924
95th percentile: 4.241635179519653
99th percentile: 4.662225122451782
mean time: 2.483428144454956
Pipeline stage StressChecker completed in 13.96s
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 2.98s
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
chaiml-nemo-espresso-ant_1376_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 0.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-nemo-espresso-ant-1376-v1-profiler
Waiting for inference service chaiml-nemo-espresso-ant-1376-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 2627.34s
Shutdown handler de-registered
chaiml-nemo-espresso-ant_1376_v1 status is now inactive due to auto deactivation removed underperforming models