chaiml-espresso-ant-llam_6735

developer_uid: azuruce

submission_id: chaiml-espresso-ant-llam_6735_v3

model_name: chaiml-espresso-ant-llam_6735_v3

model_group: ChaiML/espresso_ant_llam

status: inactive

timestamp: 2024-12-06T02:25:28+00:00

num_battles: 7547

num_wins: 3919

celo_rating: 1278.08

family_friendly_score: 0.5840000000000001

family_friendly_standard_error: 0.006970566691453429

submission_type: basic

model_repo: ChaiML/espresso_ant_llama_241204_albert_v2_sft_3epoch_128alpha

model_architecture: MistralForCausalLM

model_num_parameters: 22247282688.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.38160261701939013, 'latency_mean': 2.6204595911502837, 'latency_p50': 2.6097471714019775, 'latency_p90': 2.9132105350494384}, {'batch_size': 2, 'throughput': 0.598395388666212, 'latency_mean': 3.3332146322727203, 'latency_p50': 3.3472611904144287, 'latency_p90': 3.62712721824646}, {'batch_size': 3, 'throughput': 0.7598898299756144, 'latency_mean': 3.935984144210815, 'latency_p50': 3.935937523841858, 'latency_p90': 4.337093019485474}, {'batch_size': 4, 'throughput': 0.8781635718025453, 'latency_mean': 4.545659098625183, 'latency_p50': 4.559556722640991, 'latency_p90': 5.171977639198303}, {'batch_size': 5, 'throughput': 0.9716720241166436, 'latency_mean': 5.1181550419330595, 'latency_p50': 5.145741820335388, 'latency_p90': 5.758069801330566}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-espresso-ant-llam_6735_v3

is_internal_developer: True

language_model: ChaiML/espresso_ant_llama_241204_albert_v2_sft_3epoch_128alpha

model_size: 22B

ranking_group: single

throughput_3p7s: 0.71

us_pacific_date: 2024-12-05

win_ratio: 0.5192791837816351

generation_params: {'temperature': 0.8, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 80, '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-espresso-ant-llam-6735-v3-mkmlizer
Waiting for job on chaiml-espresso-ant-llam-6735-v3-mkmlizer to finish
chaiml-espresso-ant-llam-6735-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-espresso-ant-llam-6735-v3-mkmlizer: ║     _____            __           __                                ║
chaiml-espresso-ant-llam-6735-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-espresso-ant-llam-6735-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-espresso-ant-llam-6735-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-espresso-ant-llam-6735-v3-mkmlizer: ║       /___/                                                         ║
chaiml-espresso-ant-llam-6735-v3-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-llam-6735-v3-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-espresso-ant-llam-6735-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-espresso-ant-llam-6735-v3-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-espresso-ant-llam-6735-v3-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-llam-6735-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-espresso-ant-llam-6735-v3-mkmlizer: ║  belonging to:                                                      ║
chaiml-espresso-ant-llam-6735-v3-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-llam-6735-v3-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-espresso-ant-llam-6735-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-espresso-ant-llam-6735-v3-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-espresso-ant-llam-6735-v3-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-llam-6735-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-espresso-ant-llam-7498-v2-mkmlizer: Downloaded to shared memory in 71.589s
chaiml-espresso-ant-llam-7498-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpx0s29lnr, device:0
chaiml-espresso-ant-llam-7498-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-espresso-ant-llam-7498-v2-mkmlizer: quantized model in 45.366s
chaiml-espresso-ant-llam-7498-v2-mkmlizer: Processed model ChaiML/espresso_ant_llama_241204_albert_v2_sft_4epoch_128alpha in 116.954s
chaiml-espresso-ant-llam-7498-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-espresso-ant-llam-7498-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-espresso-ant-llam-7498-v2
chaiml-espresso-ant-llam-7498-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-espresso-ant-llam-7498-v2/config.json
chaiml-espresso-ant-llam-7498-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-espresso-ant-llam-7498-v2/special_tokens_map.json
chaiml-espresso-ant-llam-7498-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-espresso-ant-llam-7498-v2/tokenizer_config.json
chaiml-espresso-ant-llam-7498-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-espresso-ant-llam-7498-v2/tokenizer.json
chaiml-espresso-ant-llam-7498-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-espresso-ant-llam-7498-v2/flywheel_model.1.safetensors
Job chaiml-espresso-ant-llam-7498-v2-mkmlizer completed after 154.57s with status: succeeded
Stopping job with name chaiml-espresso-ant-llam-7498-v2-mkmlizer
Pipeline stage MKMLizer completed in 157.15s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.22s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-espresso-ant-llam-7498-v2
Waiting for inference service chaiml-espresso-ant-llam-7498-v2 to be ready
chaiml-espresso-ant-llam-6735-v3-mkmlizer: quantized model in 44.020s
chaiml-espresso-ant-llam-6735-v3-mkmlizer: Processed model ChaiML/espresso_ant_llama_241204_albert_v2_sft_3epoch_128alpha in 109.040s
chaiml-espresso-ant-llam-6735-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-espresso-ant-llam-6735-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-espresso-ant-llam-6735-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-espresso-ant-llam-6735-v3
chaiml-espresso-ant-llam-6735-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-espresso-ant-llam-6735-v3/config.json
chaiml-espresso-ant-llam-6735-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-espresso-ant-llam-6735-v3/special_tokens_map.json
chaiml-espresso-ant-llam-6735-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-espresso-ant-llam-6735-v3/tokenizer_config.json
chaiml-espresso-ant-llam-6735-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-espresso-ant-llam-6735-v3/tokenizer.json
chaiml-espresso-ant-llam-6735-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-espresso-ant-llam-6735-v3/flywheel_model.1.safetensors
chaiml-espresso-ant-llam-6735-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-espresso-ant-llam-6735-v3/flywheel_model.0.safetensors
chaiml-espresso-ant-llam-6735-v3-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:21, 23.38it/s]
Loading 0:   2%|▏         | 12/507 [00:00<00:12, 39.66it/s]
Loading 0:   3%|▎         | 17/507 [00:00<00:12, 38.57it/s]
Loading 0:   4%|▍         | 22/507 [00:00<00:12, 38.76it/s]
Loading 0:   5%|▌         | 27/507 [00:00<00:12, 39.95it/s]
Loading 0:   6%|▋         | 32/507 [00:00<00:14, 31.94it/s]
Loading 0:   8%|▊         | 39/507 [00:01<00:12, 38.94it/s]
Loading 0:   9%|▊         | 44/507 [00:01<00:12, 38.06it/s]
Loading 0:  10%|▉         | 49/507 [00:01<00:13, 32.95it/s]
Loading 0:  10%|█         | 53/507 [00:01<00:17, 25.25it/s]
Loading 0:  11%|█         | 56/507 [00:01<00:19, 22.74it/s]
Loading 0:  12%|█▏        | 61/507 [00:01<00:16, 27.28it/s]
Loading 0:  13%|█▎        | 65/507 [00:02<00:17, 25.50it/s]
Loading 0:  14%|█▍        | 70/507 [00:02<00:14, 29.71it/s]
Loading 0:  15%|█▍        | 75/507 [00:02<00:13, 32.55it/s]
Loading 0:  16%|█▌        | 80/507 [00:02<00:13, 32.82it/s]
Loading 0:  17%|█▋        | 87/507 [00:02<00:10, 39.21it/s]
Loading 0:  18%|█▊        | 92/507 [00:02<00:10, 38.68it/s]
Loading 0:  19%|█▉        | 97/507 [00:02<00:10, 38.22it/s]
Loading 0:  20%|█▉        | 101/507 [00:03<00:10, 38.35it/s]
Loading 0:  21%|██        | 106/507 [00:03<00:10, 38.31it/s]
Loading 0:  22%|██▏       | 110/507 [00:03<00:10, 38.15it/s]
Loading 0:  22%|██▏       | 114/507 [00:03<00:15, 24.91it/s]
Loading 0:  23%|██▎       | 118/507 [00:03<00:15, 25.54it/s]
Loading 0:  24%|██▍       | 122/507 [00:03<00:14, 25.73it/s]
Loading 0:  25%|██▌       | 129/507 [00:03<00:11, 33.27it/s]
Loading 0:  26%|██▌       | 133/507 [00:04<00:11, 33.21it/s]
Loading 0:  27%|██▋       | 138/507 [00:04<00:10, 36.47it/s]
Loading 0:  28%|██▊       | 142/507 [00:04<00:10, 35.80it/s]
Loading 0:  29%|██▉       | 147/507 [00:04<00:09, 38.74it/s]
Loading 0:  30%|██▉       | 152/507 [00:04<00:09, 38.07it/s]
Loading 0:  31%|███       | 156/507 [00:04<00:09, 38.54it/s]
Loading 0:  32%|███▏      | 160/507 [00:04<00:09, 35.19it/s]
Loading 0:  32%|███▏      | 164/507 [00:04<00:09, 34.35it/s]
Loading 0:  33%|███▎      | 169/507 [00:05<00:12, 27.14it/s]
Loading 0:  34%|███▍      | 173/507 [00:05<00:11, 28.28it/s]
Loading 0:  35%|███▍      | 177/507 [00:05<00:11, 28.11it/s]
Loading 0:  36%|███▌      | 183/507 [00:05<00:09, 34.16it/s]
Loading 0:  37%|███▋      | 187/507 [00:05<00:09, 34.15it/s]
Loading 0:  38%|███▊      | 192/507 [00:05<00:08, 37.58it/s]
Loading 0:  39%|███▊      | 196/507 [00:05<00:08, 34.97it/s]
Loading 0:  40%|███▉      | 201/507 [00:06<00:08, 37.28it/s]
Loading 0:  40%|████      | 205/507 [00:06<00:08, 35.39it/s]
Loading 0:  41%|████▏     | 210/507 [00:06<00:07, 38.14it/s]
Loading 0:  42%|████▏     | 214/507 [00:06<00:08, 35.70it/s]
Loading 0:  43%|████▎     | 218/507 [00:06<00:08, 35.62it/s]
Loading 0:  44%|████▍     | 222/507 [00:06<00:08, 34.60it/s]
Loading 0:  45%|████▍     | 226/507 [00:06<00:11, 24.69it/s]
Loading 0:  45%|████▌     | 230/507 [00:07<00:11, 24.58it/s]
Loading 0:  47%|████▋     | 237/507 [00:07<00:08, 31.63it/s]
Loading 0:  48%|████▊     | 241/507 [00:07<00:08, 31.13it/s]
Loading 0:  49%|████▊     | 246/507 [00:07<00:07, 33.72it/s]
Loading 0:  49%|████▉     | 250/507 [00:07<00:07, 33.52it/s]
Loading 0:  50%|█████     | 255/507 [00:07<00:06, 36.19it/s]
Loading 0:  51%|█████     | 259/507 [00:07<00:06, 35.56it/s]
Loading 0:  52%|█████▏    | 264/507 [00:07<00:06, 38.35it/s]
Loading 0:  53%|█████▎    | 268/507 [00:08<00:06, 37.04it/s]
Loading 0:  54%|█████▍    | 273/507 [00:08<00:05, 39.54it/s]
Loading 0:  55%|█████▍    | 278/507 [00:08<00:05, 39.37it/s]
Loading 0:  56%|█████▌    | 283/507 [00:08<00:05, 38.66it/s]
Loading 0:  57%|█████▋    | 287/507 [00:08<00:09, 23.49it/s]
Loading 0:  58%|█████▊    | 293/507 [00:08<00:07, 26.99it/s]
Loading 0:  59%|█████▉    | 299/507 [00:23<00:07, 26.99it/s]
Loading 0:  59%|█████▉    | 300/507 [00:23<02:50,  1.21it/s]
Loading 0:  60%|█████▉    | 302/507 [00:24<02:28,  1.38it/s]
Loading 0:  61%|██████    | 307/507 [00:24<01:40,  2.00it/s]
Loading 0:  61%|██████    | 310/507 [00:24<01:19,  2.47it/s]
Loading 0:  62%|██████▏   | 314/507 [00:24<00:56,  3.40it/s]
Loading 0:  63%|██████▎   | 319/507 [00:24<00:37,  4.96it/s]
Loading 0:  64%|██████▎   | 323/507 [00:24<00:28,  6.56it/s]
Loading 0:  65%|██████▍   | 328/507 [00:24<00:19,  9.09it/s]
Loading 0:  65%|██████▌   | 332/507 [00:24<00:15, 11.54it/s]
Loading 0:  66%|██████▋   | 337/507 [00:25<00:11, 15.37it/s]
Loading 0:  67%|██████▋   | 341/507 [00:25<00:10, 15.11it/s]
Loading 0:  68%|██████▊   | 345/507 [00:25<00:09, 17.40it/s]
Loading 0:  69%|██████▉   | 349/507 [00:25<00:07, 20.06it/s]
Loading 0:  70%|██████▉   | 354/507 [00:25<00:06, 24.83it/s]
Loading 0:  71%|███████   | 358/507 [00:25<00:05, 26.11it/s]
Loading 0:  72%|███████▏  | 363/507 [00:25<00:04, 30.80it/s]
Loading 0:  72%|███████▏  | 367/507 [00:26<00:04, 31.66it/s]
Loading 0:  73%|███████▎  | 372/507 [00:26<00:03, 35.39it/s]
Loading 0:  74%|███████▍  | 376/507 [00:26<00:03, 35.74it/s]
Loading 0:  75%|███████▌  | 381/507 [00:26<00:03, 39.40it/s]
Loading 0:  76%|███████▌  | 386/507 [00:26<00:03, 38.92it/s]
Loading 0:  77%|███████▋  | 391/507 [00:26<00:03, 31.96it/s]
Loading 0:  78%|███████▊  | 395/507 [00:26<00:04, 25.34it/s]
Loading 0:  79%|███████▉  | 401/507 [00:27<00:03, 26.76it/s]
Loading 0:  80%|████████  | 406/507 [00:27<00:03, 30.76it/s]
Loading 0:  81%|████████  | 410/507 [00:27<00:03, 29.68it/s]
Loading 0:  82%|████████▏ | 417/507 [00:27<00:02, 37.06it/s]
Loading 0:  83%|████████▎ | 422/507 [00:27<00:02, 37.33it/s]
Loading 0:  84%|████████▍ | 427/507 [00:27<00:02, 37.67it/s]
Loading 0:  85%|████████▌ | 431/507 [00:27<00:01, 38.11it/s]
Loading 0:  86%|████████▌ | 436/507 [00:28<00:01, 38.93it/s]
Loading 0:  87%|████████▋ | 441/507 [00:28<00:01, 41.35it/s]
Loading 0:  88%|████████▊ | 446/507 [00:28<00:01, 34.51it/s]
Loading 0:  90%|████████▉ | 454/507 [00:28<00:01, 41.46it/s]
Loading 0:  91%|█████████ | 459/507 [00:30<00:06,  6.99it/s]
Loading 0:  92%|█████████▏| 465/507 [00:30<00:04,  9.40it/s]
Loading 0:  93%|█████████▎| 472/507 [00:31<00:02, 13.22it/s]
Loading 0:  94%|█████████▍| 477/507 [00:31<00:01, 15.74it/s]
Loading 0:  95%|█████████▌| 482/507 [00:31<00:01, 18.92it/s]
Loading 0:  96%|█████████▌| 487/507 [00:31<00:00, 22.59it/s]
Loading 0:  97%|█████████▋| 492/507 [00:31<00:00, 22.66it/s]
Loading 0:  98%|█████████▊| 499/507 [00:31<00:00, 29.02it/s]
Loading 0:  99%|█████████▉| 504/507 [00:31<00:00, 31.14it/s]
                                                            
Job chaiml-espresso-ant-llam-6735-v3-mkmlizer completed after 144.44s with status: succeeded
Stopping job with name chaiml-espresso-ant-llam-6735-v3-mkmlizer
Pipeline stage MKMLizer completed in 146.62s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.24s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-espresso-ant-llam-6735-v3
Waiting for inference service chaiml-espresso-ant-llam-6735-v3 to be ready
Inference service chaiml-espresso-ant-llam-7498-v2 ready after 193.96490931510925s
Pipeline stage MKMLDeployer completed in 199.05s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.021580457687378s
Received healthy response to inference request in 2.7421748638153076s
Received healthy response to inference request in 3.2896502017974854s
Received healthy response to inference request in 2.400636672973633s
Received healthy response to inference request in 2.533207416534424s
5 requests
0 failed requests
5th percentile: 2.427150821685791
10th percentile: 2.4536649703979494
20th percentile: 2.5066932678222655
30th percentile: 2.5750009059906005
40th percentile: 2.6585878849029543
50th percentile: 2.7421748638153076
60th percentile: 2.853937101364136
70th percentile: 2.965699338912964
80th percentile: 3.0751944065093992
90th percentile: 3.1824223041534423
95th percentile: 3.236036252975464
99th percentile: 3.278927412033081
mean time: 2.7974499225616456
Pipeline stage StressChecker completed in 16.64s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Inference service chaiml-espresso-ant-llam-6735-v3 ready after 181.04185438156128s
Pipeline stage MKMLDeployer completed in 183.52s
run pipeline stage %s
Running pipeline stage StressChecker
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 2.74s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Received healthy response to inference request in 2.851942300796509s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 2.63s
Shutdown handler de-registered
chaiml-espresso-ant-llam_7498_v2 status is now deployed due to DeploymentManager action
Received healthy response to inference request in 2.6822330951690674s
Received healthy response to inference request in 2.8734562397003174s
Received healthy response to inference request in 2.9026079177856445s
Received healthy response to inference request in 2.4132468700408936s
5 requests
0 failed requests
5th percentile: 2.4670441150665283
10th percentile: 2.520841360092163
20th percentile: 2.6284358501434326
30th percentile: 2.7161749362945558
40th percentile: 2.784058618545532
50th percentile: 2.851942300796509
60th percentile: 2.8605478763580323
70th percentile: 2.869153451919556
80th percentile: 2.8792865753173826
90th percentile: 2.8909472465515136
95th percentile: 2.8967775821685793
99th percentile: 2.9014418506622315
mean time: 2.7446972846984865
Pipeline stage StressChecker completed in 15.25s
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 2.60s
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 2.34s
Shutdown handler de-registered
chaiml-espresso-ant-llam_6735_v3 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 3135.53s
Shutdown handler de-registered
chaiml-espresso-ant-llam_6735_v3 status is now inactive due to auto deactivation removed underperforming models