developer_uid: azuruce
submission_id: chaiml-espresso-ant-llam_1666_v5
model_name: chaiml-espresso-ant-llam_1666_v5
model_group: ChaiML/espresso_ant_llam
status: inactive
timestamp: 2024-12-05T07:44:51+00:00
num_battles: 10467
num_wins: 5149
celo_rating: 1257.98
family_friendly_score: 0.5813999999999999
family_friendly_standard_error: 0.006976733333014814
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': 0.3861818642457383, 'latency_mean': 2.5893657100200653, 'latency_p50': 2.5852614641189575, 'latency_p90': 2.8440561056137086}, {'batch_size': 3, 'throughput': 0.8205347046678907, 'latency_mean': 3.647309535741806, 'latency_p50': 3.6354159116744995, 'latency_p90': 3.98421950340271}, {'batch_size': 5, 'throughput': 1.0879038323290795, 'latency_mean': 4.5635213220119475, 'latency_p50': 4.55279004573822, 'latency_p90': 5.114863610267639}, {'batch_size': 6, 'throughput': 1.1740824673445347, 'latency_mean': 5.083515859842301, 'latency_p50': 5.087171673774719, 'latency_p90': 5.675779700279236}, {'batch_size': 10, 'throughput': 1.399338861978238, 'latency_mean': 7.057740931510925, 'latency_p50': 6.973400950431824, 'latency_p90': 7.886188077926636}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: chaiml-espresso-ant-llam_1666_v5
is_internal_developer: True
language_model: ChaiML/espresso_ant_llama_241204_albert_v2_sft_2epoch_128alpha
model_size: 22B
ranking_group: single
throughput_3p7s: 0.84
us_pacific_date: 2024-12-04
win_ratio: 0.49192700869399064
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', '</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-v5-mkmlizer
Connection pool is full, discarding connection: %s. Connection pool size: %s
Waiting for job on chaiml-espresso-ant-llam-1666-v5-mkmlizer to finish
chaiml-espresso-ant-llam-1666-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-espresso-ant-llam-1666-v5-mkmlizer: ║     _____            __           __                                ║
chaiml-espresso-ant-llam-1666-v5-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-espresso-ant-llam-1666-v5-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-espresso-ant-llam-1666-v5-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-espresso-ant-llam-1666-v5-mkmlizer: ║       /___/                                                         ║
chaiml-espresso-ant-llam-1666-v5-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-llam-1666-v5-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-espresso-ant-llam-1666-v5-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-espresso-ant-llam-1666-v5-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-espresso-ant-llam-1666-v5-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-llam-1666-v5-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-espresso-ant-llam-1666-v5-mkmlizer: ║  belonging to:                                                      ║
chaiml-espresso-ant-llam-1666-v5-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-llam-1666-v5-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-espresso-ant-llam-1666-v5-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-espresso-ant-llam-1666-v5-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-espresso-ant-llam-1666-v5-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-llam-1666-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-espresso-ant-llam-1666-v5-mkmlizer: Downloaded to shared memory in 44.516s
chaiml-espresso-ant-llam-1666-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpppv8jh07, device:0
chaiml-espresso-ant-llam-1666-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-espresso-ant-llam-1666-v5-mkmlizer: quantized model in 45.909s
chaiml-espresso-ant-llam-1666-v5-mkmlizer: Processed model ChaiML/espresso_ant_llama_241204_albert_v2_sft_2epoch_128alpha in 90.425s
chaiml-espresso-ant-llam-1666-v5-mkmlizer: creating bucket guanaco-mkml-models
chaiml-espresso-ant-llam-1666-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-espresso-ant-llam-1666-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v5
chaiml-espresso-ant-llam-1666-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v5/config.json
chaiml-espresso-ant-llam-1666-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v5/special_tokens_map.json
chaiml-espresso-ant-llam-1666-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v5/tokenizer_config.json
chaiml-espresso-ant-llam-1666-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v5/tokenizer.json
chaiml-espresso-ant-llam-1666-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v5/flywheel_model.1.safetensors
chaiml-espresso-ant-llam-1666-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v5/flywheel_model.0.safetensors
chaiml-espresso-ant-llam-1666-v5-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:20, 23.93it/s]
Loading 0:   2%|▏         | 12/507 [00:00<00:12, 38.29it/s]
Loading 0:   3%|▎         | 17/507 [00:00<00:13, 35.95it/s]
Loading 0:   4%|▍         | 21/507 [00:00<00:13, 36.66it/s]
Loading 0:   5%|▍         | 25/507 [00:00<00:14, 33.62it/s]
Loading 0:   6%|▌         | 30/507 [00:00<00:13, 35.61it/s]
Loading 0:   7%|▋         | 34/507 [00:01<00:14, 32.32it/s]
Loading 0:   8%|▊         | 39/507 [00:01<00:13, 34.69it/s]
Loading 0:   8%|▊         | 43/507 [00:01<00:13, 33.16it/s]
Loading 0:   9%|▉         | 47/507 [00:01<00:13, 33.17it/s]
Loading 0:  10%|█         | 51/507 [00:01<00:14, 32.09it/s]
Loading 0:  11%|█         | 55/507 [00:01<00:20, 21.87it/s]
Loading 0:  11%|█▏        | 58/507 [00:01<00:19, 22.84it/s]
Loading 0:  12%|█▏        | 63/507 [00:02<00:16, 26.66it/s]
Loading 0:  13%|█▎        | 66/507 [00:02<00:17, 25.47it/s]
Loading 0:  14%|█▍        | 70/507 [00:02<00:15, 28.01it/s]
Loading 0:  15%|█▍        | 75/507 [00:02<00:13, 31.85it/s]
Loading 0:  16%|█▌        | 80/507 [00:02<00:13, 31.14it/s]
Loading 0:  17%|█▋        | 85/507 [00:02<00:11, 35.34it/s]
Loading 0:  18%|█▊        | 89/507 [00:02<00:13, 30.90it/s]
Loading 0:  19%|█▊        | 94/507 [00:03<00:11, 34.86it/s]
Loading 0:  19%|█▉        | 98/507 [00:03<00:13, 30.03it/s]
Loading 0:  20%|██        | 103/507 [00:03<00:11, 34.49it/s]
Loading 0:  21%|██        | 107/507 [00:03<00:13, 30.44it/s]
Loading 0:  22%|██▏       | 112/507 [00:03<00:11, 34.11it/s]
Loading 0:  23%|██▎       | 116/507 [00:03<00:17, 22.16it/s]
Loading 0:  24%|██▍       | 122/507 [00:04<00:15, 24.80it/s]
Loading 0:  25%|██▌       | 127/507 [00:04<00:13, 28.78it/s]
Loading 0:  26%|██▌       | 131/507 [00:04<00:13, 27.04it/s]
Loading 0:  27%|██▋       | 136/507 [00:04<00:11, 31.36it/s]
Loading 0:  28%|██▊       | 140/507 [00:04<00:12, 29.31it/s]
Loading 0:  29%|██▊       | 145/507 [00:04<00:10, 33.65it/s]
Loading 0:  29%|██▉       | 149/507 [00:04<00:11, 30.34it/s]
Loading 0:  30%|███       | 154/507 [00:05<00:10, 34.52it/s]
Loading 0:  31%|███       | 158/507 [00:05<00:11, 31.18it/s]
Loading 0:  32%|███▏      | 164/507 [00:05<00:09, 35.77it/s]
Loading 0:  33%|███▎      | 169/507 [00:05<00:12, 27.57it/s]
Loading 0:  34%|███▍      | 173/507 [00:05<00:11, 27.89it/s]
Loading 0:  35%|███▍      | 177/507 [00:05<00:12, 26.67it/s]
Loading 0:  36%|███▌      | 183/507 [00:06<00:10, 31.62it/s]
Loading 0:  37%|███▋      | 187/507 [00:06<00:10, 30.79it/s]
Loading 0:  38%|███▊      | 192/507 [00:06<00:09, 33.34it/s]
Loading 0:  39%|███▊      | 196/507 [00:06<00:09, 31.61it/s]
Loading 0:  39%|███▉      | 200/507 [00:06<00:09, 33.53it/s]
Loading 0:  40%|████      | 204/507 [00:06<00:10, 29.52it/s]
Loading 0:  41%|████      | 209/507 [00:06<00:08, 34.19it/s]
Loading 0:  42%|████▏     | 213/507 [00:06<00:09, 30.50it/s]
Loading 0:  43%|████▎     | 218/507 [00:07<00:08, 32.84it/s]
Loading 0:  44%|████▍     | 222/507 [00:07<00:09, 31.48it/s]
Loading 0:  45%|████▍     | 226/507 [00:07<00:12, 22.76it/s]
Loading 0:  45%|████▌     | 230/507 [00:07<00:12, 22.63it/s]
Loading 0:  46%|████▋     | 235/507 [00:07<00:09, 27.67it/s]
Loading 0:  47%|████▋     | 239/507 [00:08<00:10, 26.25it/s]
Loading 0:  48%|████▊     | 244/507 [00:08<00:08, 30.63it/s]
Loading 0:  49%|████▉     | 248/507 [00:08<00:09, 28.11it/s]
Loading 0:  50%|████▉     | 253/507 [00:08<00:07, 32.36it/s]
Loading 0:  51%|█████     | 257/507 [00:08<00:08, 29.01it/s]
Loading 0:  52%|█████▏    | 262/507 [00:08<00:07, 32.65it/s]
Loading 0:  52%|█████▏    | 266/507 [00:08<00:08, 29.23it/s]
Loading 0:  53%|█████▎    | 271/507 [00:08<00:07, 33.16it/s]
Loading 0:  54%|█████▍    | 275/507 [00:09<00:07, 30.14it/s]
Loading 0:  55%|█████▌    | 280/507 [00:09<00:06, 34.13it/s]
Loading 0:  56%|█████▌    | 284/507 [00:09<00:08, 25.25it/s]
Loading 0:  57%|█████▋    | 288/507 [00:09<00:08, 24.98it/s]
Loading 0:  58%|█████▊    | 293/507 [00:09<00:08, 25.73it/s]
Loading 0:  59%|█████▉    | 298/507 [00:09<00:06, 29.91it/s]
Loading 0:  59%|█████▉    | 299/507 [00:19<00:06, 29.91it/s]
Loading 0:  59%|█████▉    | 300/507 [00:24<04:00,  1.16s/it]
Loading 0:  60%|█████▉    | 302/507 [00:24<03:17,  1.04it/s]
Loading 0:  61%|██████    | 307/507 [00:24<01:59,  1.67it/s]
Loading 0:  61%|██████    | 310/507 [00:25<01:30,  2.18it/s]
Loading 0:  62%|██████▏   | 313/507 [00:25<01:07,  2.89it/s]
Loading 0:  63%|██████▎   | 318/507 [00:25<00:41,  4.53it/s]
Loading 0:  64%|██████▎   | 322/507 [00:25<00:30,  6.08it/s]
Loading 0:  64%|██████▍   | 327/507 [00:25<00:20,  8.71it/s]
Loading 0:  65%|██████▌   | 331/507 [00:25<00:16, 10.92it/s]
Loading 0:  66%|██████▌   | 335/507 [00:25<00:12, 13.54it/s]
Loading 0:  67%|██████▋   | 340/507 [00:26<00:11, 14.91it/s]
Loading 0:  68%|██████▊   | 343/507 [00:26<00:10, 16.21it/s]
Loading 0:  68%|██████▊   | 347/507 [00:26<00:08, 18.12it/s]
Loading 0:  70%|██████▉   | 354/507 [00:26<00:06, 25.34it/s]
Loading 0:  71%|███████   | 358/507 [00:26<00:05, 26.41it/s]
Loading 0:  72%|███████▏  | 363/507 [00:26<00:04, 29.95it/s]
Loading 0:  72%|███████▏  | 367/507 [00:26<00:04, 29.88it/s]
Loading 0:  73%|███████▎  | 372/507 [00:26<00:04, 32.80it/s]
Loading 0:  74%|███████▍  | 376/507 [00:27<00:04, 32.62it/s]
Loading 0:  75%|███████▌  | 381/507 [00:27<00:03, 35.09it/s]
Loading 0:  76%|███████▌  | 385/507 [00:27<00:03, 33.09it/s]
Loading 0:  77%|███████▋  | 389/507 [00:27<00:03, 33.22it/s]
Loading 0:  78%|███████▊  | 393/507 [00:27<00:03, 32.75it/s]
Loading 0:  78%|███████▊  | 397/507 [00:27<00:04, 24.22it/s]
Loading 0:  79%|███████▉  | 401/507 [00:28<00:04, 24.00it/s]
Loading 0:  80%|████████  | 406/507 [00:28<00:03, 28.92it/s]
Loading 0:  81%|████████  | 410/507 [00:28<00:03, 28.09it/s]
Loading 0:  82%|████████▏ | 417/507 [00:28<00:02, 35.29it/s]
Loading 0:  83%|████████▎ | 421/507 [00:28<00:02, 33.74it/s]
Loading 0:  84%|████████▍ | 426/507 [00:28<00:02, 35.70it/s]
Loading 0:  85%|████████▍ | 430/507 [00:28<00:02, 33.84it/s]
Loading 0:  86%|████████▌ | 435/507 [00:28<00:01, 36.27it/s]
Loading 0:  87%|████████▋ | 439/507 [00:29<00:01, 34.76it/s]
Loading 0:  88%|████████▊ | 444/507 [00:29<00:01, 36.93it/s]
Loading 0:  88%|████████▊ | 448/507 [00:29<00:01, 34.73it/s]
Loading 0:  89%|████████▉ | 453/507 [00:29<00:01, 38.49it/s]
Loading 0:  90%|█████████ | 457/507 [00:31<00:08,  5.78it/s]
Loading 0:  91%|█████████ | 460/507 [00:31<00:06,  6.92it/s]
Loading 0:  92%|█████████▏| 465/507 [00:31<00:04,  9.46it/s]
Loading 0:  93%|█████████▎| 472/507 [00:32<00:02, 14.34it/s]
Loading 0:  94%|█████████▍| 476/507 [00:32<00:01, 16.44it/s]
Loading 0:  95%|█████████▍| 480/507 [00:32<00:01, 19.06it/s]
Loading 0:  95%|█████████▌| 484/507 [00:32<00:01, 20.41it/s]
Loading 0:  96%|█████████▋| 488/507 [00:32<00:00, 23.53it/s]
Loading 0:  97%|█████████▋| 492/507 [00:32<00:00, 23.71it/s]
Loading 0:  98%|█████████▊| 497/507 [00:32<00:00, 28.77it/s]
Loading 0:  99%|█████████▉| 501/507 [00:33<00:00, 27.38it/s]
Loading 0: 100%|█████████▉| 506/507 [00:33<00:00, 31.68it/s]
                                                            

Job chaiml-espresso-ant-llam-1666-v5-mkmlizer completed after 132.21s with status: succeeded
Stopping job with name chaiml-espresso-ant-llam-1666-v5-mkmlizer
Pipeline stage MKMLizer completed in 133.82s
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-v5
Waiting for inference service chaiml-espresso-ant-llam-1666-v5 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
Inference service chaiml-espresso-ant-llam-1666-v5 ready after 184.96331453323364s
Pipeline stage MKMLDeployer completed in 186.56s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.3267741203308105s
Received healthy response to inference request in 2.5085442066192627s
Received healthy response to inference request in 2.2018158435821533s
Received healthy response to inference request in 2.2776973247528076s
Received healthy response to inference request in 2.75069260597229s
5 requests
0 failed requests
5th percentile: 2.216992139816284
10th percentile: 2.232168436050415
20th percentile: 2.2625210285186768
30th percentile: 2.3238667011260987
40th percentile: 2.4162054538726805
50th percentile: 2.5085442066192627
60th percentile: 2.6054035663604735
70th percentile: 2.7022629261016844
80th percentile: 2.8659089088439944
90th percentile: 3.0963415145874023
95th percentile: 3.211557817459106
99th percentile: 3.30373085975647
mean time: 2.613104820251465
Pipeline stage StressChecker completed in 14.50s
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 2.43s
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 2.39s
Shutdown handler de-registered
chaiml-espresso-ant-llam_1666_v5 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 chaiml-espresso-ant-llam-1666-v5-profiler
Waiting for inference service chaiml-espresso-ant-llam-1666-v5-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 3115.47s
Shutdown handler de-registered
chaiml-espresso-ant-llam_1666_v5 status is now inactive due to auto deactivation removed underperforming models