chaiml-espresso-ant-llam_1666

developer_uid: azuruce

submission_id: chaiml-espresso-ant-llam_1666_v8

model_name: chaiml-espresso-ant-llam_1666_v8

model_group: ChaiML/espresso_ant_llam

status: inactive

timestamp: 2024-12-05T08:13:13+00:00

num_battles: 12063

num_wins: 5939

celo_rating: 1257.64

family_friendly_score: 0.5860000000000001

family_friendly_standard_error: 0.006965687331484238

submission_type: basic

model_repo: ChaiML/espresso_ant_llama_241204_albert_v2_sft_2epoch_128alpha

model_architecture: MistralForCausalLM

model_num_parameters: 22247282688.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.39399877380104686, 'latency_mean': 2.538015958070755, 'latency_p50': 2.5217820405960083, 'latency_p90': 2.8357420206069945}, {'batch_size': 3, 'throughput': 0.8227086717139115, 'latency_mean': 3.636029860973358, 'latency_p50': 3.6325567960739136, 'latency_p90': 3.997766947746277}, {'batch_size': 5, 'throughput': 1.089518440101495, 'latency_mean': 4.559674898386001, 'latency_p50': 4.575956583023071, 'latency_p90': 5.1126017570495605}, {'batch_size': 6, 'throughput': 1.1865584849127724, 'latency_mean': 5.033909205198288, 'latency_p50': 5.0532602071762085, 'latency_p90': 5.760063552856445}, {'batch_size': 10, 'throughput': 1.4037312196471714, 'latency_mean': 7.064072448015213, 'latency_p50': 7.026779532432556, 'latency_p90': 7.940499615669251}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-espresso-ant-llam_1666_v8

is_internal_developer: True

language_model: ChaiML/espresso_ant_llama_241204_albert_v2_sft_2epoch_128alpha

model_size: 22B

ranking_group: single

throughput_3p7s: 0.85

us_pacific_date: 2024-12-05

win_ratio: 0.4923319240653237

generation_params: {'temperature': 0.75, '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-espresso-ant-llam-1666-v8-mkmlizer
Waiting for job on chaiml-espresso-ant-llam-1666-v8-mkmlizer to finish
chaiml-espresso-ant-llam-1666-v8-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-espresso-ant-llam-1666-v8-mkmlizer: ║     _____            __           __                                ║
chaiml-espresso-ant-llam-1666-v8-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-espresso-ant-llam-1666-v8-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-espresso-ant-llam-1666-v8-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-espresso-ant-llam-1666-v8-mkmlizer: ║       /___/                                                         ║
chaiml-espresso-ant-llam-1666-v8-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-llam-1666-v8-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-espresso-ant-llam-1666-v8-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-espresso-ant-llam-1666-v8-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-espresso-ant-llam-1666-v8-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-llam-1666-v8-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-espresso-ant-llam-1666-v8-mkmlizer: ║  belonging to:                                                      ║
chaiml-espresso-ant-llam-1666-v8-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-llam-1666-v8-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-espresso-ant-llam-1666-v8-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-espresso-ant-llam-1666-v8-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-espresso-ant-llam-1666-v8-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-llam-1666-v8-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-espresso-ant-llam-1666-v8-mkmlizer: Downloaded to shared memory in 43.048s
chaiml-espresso-ant-llam-1666-v8-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpp4ie6_tx, device:0
chaiml-espresso-ant-llam-1666-v8-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-espresso-ant-llam-1666-v8-mkmlizer: quantized model in 46.137s
chaiml-espresso-ant-llam-1666-v8-mkmlizer: Processed model ChaiML/espresso_ant_llama_241204_albert_v2_sft_2epoch_128alpha in 89.185s
chaiml-espresso-ant-llam-1666-v8-mkmlizer: creating bucket guanaco-mkml-models
chaiml-espresso-ant-llam-1666-v8-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-espresso-ant-llam-1666-v8-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v8
chaiml-espresso-ant-llam-1666-v8-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v8/special_tokens_map.json
chaiml-espresso-ant-llam-1666-v8-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v8/config.json
chaiml-espresso-ant-llam-1666-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v8/tokenizer_config.json
chaiml-espresso-ant-llam-1666-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v8/tokenizer.json
chaiml-espresso-ant-llam-1666-v8-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v8/flywheel_model.1.safetensors
chaiml-espresso-ant-llam-1666-v8-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v8/flywheel_model.0.safetensors
chaiml-espresso-ant-llam-1666-v8-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:25, 20.04it/s]
Loading 0:   2%|▏         | 10/507 [00:00<00:17, 28.32it/s]
Loading 0:   3%|▎         | 14/507 [00:00<00:19, 24.66it/s]
Loading 0:   4%|▎         | 19/507 [00:00<00:16, 29.90it/s]
Loading 0:   5%|▍         | 23/507 [00:00<00:18, 26.77it/s]
Loading 0:   6%|▌         | 28/507 [00:00<00:15, 30.61it/s]
Loading 0:   6%|▋         | 32/507 [00:01<00:17, 27.24it/s]
Loading 0:   7%|▋         | 37/507 [00:01<00:14, 31.56it/s]
Loading 0:   8%|▊         | 41/507 [00:01<00:16, 28.57it/s]
Loading 0:   9%|▉         | 47/507 [00:01<00:13, 33.15it/s]
Loading 0:  10%|█         | 51/507 [00:01<00:13, 33.18it/s]
Loading 0:  11%|█         | 55/507 [00:02<00:20, 22.52it/s]
Loading 0:  11%|█▏        | 58/507 [00:02<00:18, 23.65it/s]
Loading 0:  12%|█▏        | 63/507 [00:02<00:16, 27.73it/s]
Loading 0:  13%|█▎        | 67/507 [00:02<00:15, 28.49it/s]
Loading 0:  14%|█▍        | 71/507 [00:02<00:14, 29.88it/s]
Loading 0:  15%|█▍        | 75/507 [00:02<00:14, 29.76it/s]
Loading 0:  16%|█▌        | 80/507 [00:02<00:14, 28.82it/s]
Loading 0:  17%|█▋        | 85/507 [00:02<00:13, 31.44it/s]
Loading 0:  18%|█▊        | 89/507 [00:03<00:15, 26.29it/s]
Loading 0:  19%|█▊        | 94/507 [00:03<00:13, 30.40it/s]
Loading 0:  19%|█▉        | 98/507 [00:03<00:14, 27.74it/s]
Loading 0:  20%|██        | 103/507 [00:03<00:12, 32.03it/s]
Loading 0:  21%|██        | 107/507 [00:03<00:14, 28.38it/s]
Loading 0:  22%|██▏       | 112/507 [00:03<00:12, 30.43it/s]
Loading 0:  23%|██▎       | 116/507 [00:04<00:20, 18.83it/s]
Loading 0:  24%|██▍       | 122/507 [00:04<00:17, 21.87it/s]
Loading 0:  25%|██▌       | 127/507 [00:04<00:15, 25.10it/s]
Loading 0:  26%|██▌       | 131/507 [00:04<00:16, 23.07it/s]
Loading 0:  27%|██▋       | 136/507 [00:05<00:13, 26.85it/s]
Loading 0:  28%|██▊       | 140/507 [00:05<00:14, 25.66it/s]
Loading 0:  29%|██▊       | 145/507 [00:05<00:12, 29.69it/s]
Loading 0:  29%|██▉       | 149/507 [00:05<00:13, 27.17it/s]
Loading 0:  30%|███       | 154/507 [00:05<00:11, 30.49it/s]
Loading 0:  31%|███       | 158/507 [00:05<00:12, 28.20it/s]
Loading 0:  32%|███▏      | 163/507 [00:05<00:10, 32.09it/s]
Loading 0:  33%|███▎      | 168/507 [00:05<00:09, 34.56it/s]
Loading 0:  34%|███▍      | 172/507 [00:06<00:13, 24.11it/s]
Loading 0:  35%|███▍      | 176/507 [00:06<00:13, 25.18it/s]
Loading 0:  36%|███▌      | 183/507 [00:06<00:09, 32.97it/s]
Loading 0:  37%|███▋      | 187/507 [00:06<00:10, 30.58it/s]
Loading 0:  38%|███▊      | 191/507 [00:06<00:10, 31.25it/s]
Loading 0:  38%|███▊      | 195/507 [00:07<00:11, 28.09it/s]
Loading 0:  39%|███▉      | 199/507 [00:07<00:10, 29.29it/s]
Loading 0:  40%|████      | 203/507 [00:07<00:11, 26.14it/s]
Loading 0:  41%|████      | 208/507 [00:07<00:09, 30.15it/s]
Loading 0:  42%|████▏     | 212/507 [00:07<00:10, 28.15it/s]
Loading 0:  43%|████▎     | 217/507 [00:07<00:08, 32.92it/s]
Loading 0:  44%|████▎     | 221/507 [00:07<00:09, 30.03it/s]
Loading 0:  44%|████▍     | 225/507 [00:08<00:13, 20.33it/s]
Loading 0:  45%|████▌     | 230/507 [00:08<00:12, 21.94it/s]
Loading 0:  46%|████▋     | 235/507 [00:08<00:10, 25.88it/s]
Loading 0:  47%|████▋     | 239/507 [00:08<00:11, 23.96it/s]
Loading 0:  48%|████▊     | 244/507 [00:08<00:09, 27.69it/s]
Loading 0:  49%|████▉     | 248/507 [00:09<00:10, 24.99it/s]
Loading 0:  50%|████▉     | 253/507 [00:09<00:09, 27.62it/s]
Loading 0:  51%|█████     | 257/507 [00:09<00:09, 25.66it/s]
Loading 0:  52%|█████▏    | 262/507 [00:09<00:08, 29.55it/s]
Loading 0:  52%|█████▏    | 266/507 [00:09<00:09, 26.64it/s]
Loading 0:  53%|█████▎    | 271/507 [00:09<00:07, 29.75it/s]
Loading 0:  54%|█████▍    | 275/507 [00:10<00:08, 27.74it/s]
Loading 0:  55%|█████▌    | 280/507 [00:10<00:07, 32.19it/s]
Loading 0:  56%|█████▌    | 284/507 [00:10<00:08, 24.94it/s]
Loading 0:  57%|█████▋    | 287/507 [00:10<00:09, 23.42it/s]
Loading 0:  58%|█████▊    | 293/507 [00:10<00:08, 26.70it/s]
Loading 0:  59%|█████▉    | 299/507 [00:25<00:07, 26.70it/s]
Loading 0:  59%|█████▉    | 300/507 [00:25<02:59,  1.16it/s]
Loading 0:  60%|█████▉    | 302/507 [00:25<02:35,  1.32it/s]
Loading 0:  61%|██████    | 307/507 [00:25<01:43,  1.93it/s]
Loading 0:  61%|██████    | 310/507 [00:26<01:21,  2.43it/s]
Loading 0:  62%|██████▏   | 313/507 [00:26<01:02,  3.10it/s]
Loading 0:  62%|██████▏   | 316/507 [00:26<00:47,  4.02it/s]
Loading 0:  63%|██████▎   | 320/507 [00:26<00:33,  5.51it/s]
Loading 0:  64%|██████▍   | 325/507 [00:26<00:22,  8.17it/s]
Loading 0:  65%|██████▍   | 329/507 [00:26<00:17, 10.21it/s]
Loading 0:  66%|██████▌   | 334/507 [00:26<00:12, 14.02it/s]
Loading 0:  67%|██████▋   | 339/507 [00:26<00:09, 18.20it/s]
Loading 0:  68%|██████▊   | 343/507 [00:27<00:09, 16.52it/s]
Loading 0:  68%|██████▊   | 347/507 [00:27<00:08, 18.34it/s]
Loading 0:  70%|██████▉   | 354/507 [00:27<00:05, 25.89it/s]
Loading 0:  71%|███████   | 358/507 [00:27<00:05, 27.18it/s]
Loading 0:  72%|███████▏  | 363/507 [00:27<00:04, 31.13it/s]
Loading 0:  72%|███████▏  | 367/507 [00:27<00:04, 31.54it/s]
Loading 0:  73%|███████▎  | 372/507 [00:27<00:03, 35.21it/s]
Loading 0:  74%|███████▍  | 377/507 [00:28<00:03, 36.39it/s]
Loading 0:  75%|███████▌  | 382/507 [00:28<00:03, 37.62it/s]
Loading 0:  76%|███████▋  | 387/507 [00:28<00:03, 39.73it/s]
Loading 0:  77%|███████▋  | 392/507 [00:28<00:03, 34.71it/s]
Loading 0:  78%|███████▊  | 396/507 [00:28<00:04, 26.18it/s]
Loading 0:  79%|███████▉  | 401/507 [00:28<00:03, 27.33it/s]
Loading 0:  80%|████████  | 408/507 [00:29<00:02, 33.97it/s]
Loading 0:  81%|████████▏ | 412/507 [00:29<00:02, 33.27it/s]
Loading 0:  82%|████████▏ | 417/507 [00:29<00:02, 35.95it/s]
Loading 0:  83%|████████▎ | 421/507 [00:29<00:02, 35.03it/s]
Loading 0:  84%|████████▍ | 426/507 [00:29<00:02, 37.99it/s]
Loading 0:  85%|████████▍ | 430/507 [00:29<00:02, 36.29it/s]
Loading 0:  86%|████████▌ | 435/507 [00:29<00:01, 38.86it/s]
Loading 0:  87%|████████▋ | 439/507 [00:29<00:01, 37.44it/s]
Loading 0:  88%|████████▊ | 444/507 [00:30<00:01, 40.15it/s]
Loading 0:  89%|████████▊ | 449/507 [00:30<00:01, 39.80it/s]
Loading 0:  90%|████████▉ | 454/507 [00:30<00:01, 38.82it/s]
Loading 0:  90%|█████████ | 458/507 [00:32<00:07,  6.14it/s]
Loading 0:  91%|█████████ | 461/507 [00:32<00:06,  7.36it/s]
Loading 0:  92%|█████████▏| 465/507 [00:32<00:04,  9.27it/s]
Loading 0:  93%|█████████▎| 472/507 [00:32<00:02, 14.36it/s]
Loading 0:  94%|█████████▍| 476/507 [00:33<00:01, 16.80it/s]
Loading 0:  95%|█████████▍| 481/507 [00:33<00:01, 20.86it/s]
Loading 0:  96%|█████████▌| 485/507 [00:33<00:00, 23.05it/s]
Loading 0:  97%|█████████▋| 490/507 [00:33<00:00, 27.03it/s]
Loading 0:  97%|█████████▋| 494/507 [00:33<00:00, 28.25it/s]
Loading 0:  98%|█████████▊| 499/507 [00:33<00:00, 31.58it/s]
Loading 0:  99%|█████████▉| 503/507 [00:33<00:00, 31.52it/s]
                                                            
Job chaiml-espresso-ant-llam-1666-v8-mkmlizer completed after 121.04s with status: succeeded
Stopping job with name chaiml-espresso-ant-llam-1666-v8-mkmlizer
Pipeline stage MKMLizer completed in 122.46s
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-espresso-ant-llam-1666-v8
Waiting for inference service chaiml-espresso-ant-llam-1666-v8 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
Inference service chaiml-espresso-ant-llam-1666-v8 ready after 175.29876232147217s
Pipeline stage MKMLDeployer completed in 176.88s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.394516944885254s
Received healthy response to inference request in 2.5570051670074463s
Received healthy response to inference request in 2.370258092880249s
Received healthy response to inference request in 2.2440123558044434s
Received healthy response to inference request in 2.361752510070801s
5 requests
0 failed requests
5th percentile: 2.2675603866577148
10th percentile: 2.291108417510986
20th percentile: 2.3382044792175294
30th percentile: 2.3634536266326904
40th percentile: 2.3668558597564697
50th percentile: 2.370258092880249
60th percentile: 2.444956922531128
70th percentile: 2.5196557521820067
80th percentile: 2.724507522583008
90th percentile: 3.059512233734131
95th percentile: 3.227014589309692
99th percentile: 3.3610164737701416
mean time: 2.585509014129639
Pipeline stage StressChecker completed in 14.14s
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 2.18s
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 2.07s
Shutdown handler de-registered
chaiml-espresso-ant-llam_1666_v8 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 3179.74s
Shutdown handler de-registered
chaiml-espresso-ant-llam_1666_v8 status is now inactive due to auto deactivation removed underperforming models