chaiml-espresso-ant-llam_1666

developer_uid: azuruce

submission_id: chaiml-espresso-ant-llam_1666_v4

model_name: chaiml-espresso-ant-llam_1666_v4

model_group: ChaiML/espresso_ant_llam

status: inactive

timestamp: 2024-12-05T07:08:08+00:00

num_battles: 11655

num_wins: 5631

celo_rating: 1252.11

family_friendly_score: 0.5831999999999999

family_friendly_standard_error: 0.006972485353157796

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': 0.3908141534887436, 'latency_mean': 2.5586976182460783, 'latency_p50': 2.5540478229522705, 'latency_p90': 2.830591416358948}, {'batch_size': 3, 'throughput': 0.8276528068002856, 'latency_mean': 3.616407572031021, 'latency_p50': 3.639650821685791, 'latency_p90': 3.9618826150894164}, {'batch_size': 5, 'throughput': 1.100631792171001, 'latency_mean': 4.517662110328675, 'latency_p50': 4.506086945533752, 'latency_p90': 5.123766088485717}, {'batch_size': 6, 'throughput': 1.1811836860707328, 'latency_mean': 5.036843403577804, 'latency_p50': 5.008619070053101, 'latency_p90': 5.7356304168701175}, {'batch_size': 10, 'throughput': 1.3989047593092236, 'latency_mean': 7.082585808038711, 'latency_p50': 6.992168664932251, 'latency_p90': 8.076030421257018}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-espresso-ant-llam_1666_v4

is_internal_developer: True

language_model: ChaiML/espresso_ant_llama_241204_albert_v2_sft_2epoch_128alpha

model_size: 22B

ranking_group: single

throughput_3p7s: 0.86

us_pacific_date: 2024-12-04

win_ratio: 0.4831402831402831

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-espresso-ant-llam-1666-v4-mkmlizer
Waiting for job on chaiml-espresso-ant-llam-1666-v4-mkmlizer to finish
Stopping job with name chaiml-espresso-ant-llam-1666-v4-mkmlizer
%s, retrying in %s seconds...
Starting job with name chaiml-espresso-ant-llam-1666-v4-mkmlizer
Waiting for job on chaiml-espresso-ant-llam-1666-v4-mkmlizer to finish
chaiml-espresso-ant-llam-1666-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-espresso-ant-llam-1666-v4-mkmlizer: ║     _____            __           __                                ║
chaiml-espresso-ant-llam-1666-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-espresso-ant-llam-1666-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-espresso-ant-llam-1666-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-espresso-ant-llam-1666-v4-mkmlizer: ║       /___/                                                         ║
chaiml-espresso-ant-llam-1666-v4-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-llam-1666-v4-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-espresso-ant-llam-1666-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-espresso-ant-llam-1666-v4-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-espresso-ant-llam-1666-v4-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-llam-1666-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-espresso-ant-llam-1666-v4-mkmlizer: ║  belonging to:                                                      ║
chaiml-espresso-ant-llam-1666-v4-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-llam-1666-v4-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-espresso-ant-llam-1666-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-espresso-ant-llam-1666-v4-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-espresso-ant-llam-1666-v4-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-llam-1666-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission chaiml-espresso-ant-2412_7481_v2: ('http://chaiml-espresso-ant-2412-7481-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:50472->127.0.0.1:8080: read: connection reset by peer\n')
chaiml-espresso-ant-llam-1666-v4-mkmlizer: Downloaded to shared memory in 40.927s
chaiml-espresso-ant-llam-1666-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpm3qafx0k, device:0
chaiml-espresso-ant-llam-1666-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-espresso-ant-llam-1666-v4-mkmlizer: quantized model in 44.022s
chaiml-espresso-ant-llam-1666-v4-mkmlizer: Processed model ChaiML/espresso_ant_llama_241204_albert_v2_sft_2epoch_128alpha in 84.949s
chaiml-espresso-ant-llam-1666-v4-mkmlizer: creating bucket guanaco-mkml-models
chaiml-espresso-ant-llam-1666-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-espresso-ant-llam-1666-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v4
chaiml-espresso-ant-llam-1666-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v4/special_tokens_map.json
chaiml-espresso-ant-llam-1666-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v4/config.json
chaiml-espresso-ant-llam-1666-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v4/tokenizer_config.json
chaiml-espresso-ant-llam-1666-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v4/tokenizer.json
chaiml-espresso-ant-llam-1666-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v4/flywheel_model.1.safetensors
chaiml-espresso-ant-llam-1666-v4-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:19, 26.17it/s]
Loading 0:   2%|▏         | 12/507 [00:00<00:11, 43.34it/s]
Loading 0:   3%|▎         | 17/507 [00:00<00:12, 40.43it/s]
Loading 0:   4%|▍         | 22/507 [00:00<00:12, 40.15it/s]
Loading 0:   5%|▌         | 27/507 [00:00<00:11, 40.54it/s]
Loading 0:   6%|▋         | 32/507 [00:00<00:13, 34.12it/s]
Loading 0:   8%|▊         | 39/507 [00:00<00:11, 41.49it/s]
Loading 0:   9%|▊         | 44/507 [00:01<00:11, 40.57it/s]
Loading 0:  10%|▉         | 49/507 [00:01<00:13, 34.22it/s]
Loading 0:  10%|█         | 53/507 [00:01<00:18, 24.70it/s]
Loading 0:  11%|█         | 56/507 [00:01<00:19, 22.74it/s]
Loading 0:  12%|█▏        | 63/507 [00:01<00:14, 29.61it/s]
Loading 0:  13%|█▎        | 67/507 [00:02<00:14, 29.89it/s]
Loading 0:  14%|█▍        | 72/507 [00:02<00:12, 33.82it/s]
Loading 0:  15%|█▌        | 78/507 [00:02<00:11, 38.76it/s]
Loading 0:  16%|█▋        | 83/507 [00:02<00:11, 36.72it/s]
Loading 0:  17%|█▋        | 87/507 [00:02<00:11, 36.92it/s]
Loading 0:  18%|█▊        | 91/507 [00:02<00:11, 35.28it/s]
Loading 0:  19%|█▉        | 96/507 [00:02<00:11, 36.11it/s]
Loading 0:  20%|█▉        | 100/507 [00:02<00:12, 33.69it/s]
Loading 0:  21%|██        | 105/507 [00:03<00:11, 34.84it/s]
Loading 0:  21%|██▏       | 109/507 [00:03<00:11, 34.38it/s]
Loading 0:  22%|██▏       | 113/507 [00:03<00:15, 25.13it/s]
Loading 0:  23%|██▎       | 116/507 [00:03<00:17, 22.61it/s]
Loading 0:  24%|██▍       | 122/507 [00:03<00:15, 25.44it/s]
Loading 0:  25%|██▌       | 127/507 [00:03<00:13, 29.20it/s]
Loading 0:  26%|██▌       | 131/507 [00:04<00:13, 27.65it/s]
Loading 0:  27%|██▋       | 138/507 [00:04<00:10, 34.73it/s]
Loading 0:  28%|██▊       | 142/507 [00:04<00:10, 33.77it/s]
Loading 0:  29%|██▉       | 147/507 [00:04<00:09, 36.57it/s]
Loading 0:  30%|██▉       | 151/507 [00:04<00:10, 34.49it/s]
Loading 0:  31%|███       | 156/507 [00:04<00:09, 35.57it/s]
Loading 0:  32%|███▏      | 160/507 [00:04<00:10, 33.93it/s]
Loading 0:  32%|███▏      | 164/507 [00:04<00:09, 34.32it/s]
Loading 0:  33%|███▎      | 169/507 [00:05<00:12, 27.09it/s]
Loading 0:  34%|███▍      | 173/507 [00:05<00:11, 28.31it/s]
Loading 0:  35%|███▍      | 177/507 [00:05<00:11, 28.08it/s]
Loading 0:  36%|███▌      | 181/507 [00:05<00:10, 30.54it/s]
Loading 0:  36%|███▋      | 185/507 [00:05<00:10, 29.44it/s]
Loading 0:  38%|███▊      | 192/507 [00:05<00:08, 37.23it/s]
Loading 0:  39%|███▊      | 196/507 [00:06<00:08, 35.08it/s]
Loading 0:  40%|███▉      | 201/507 [00:06<00:08, 37.06it/s]
Loading 0:  40%|████      | 205/507 [00:06<00:08, 35.56it/s]
Loading 0:  41%|████▏     | 210/507 [00:06<00:07, 37.92it/s]
Loading 0:  42%|████▏     | 214/507 [00:06<00:08, 36.29it/s]
Loading 0:  43%|████▎     | 218/507 [00:06<00:07, 36.44it/s]
Loading 0:  44%|████▍     | 222/507 [00:06<00:08, 35.04it/s]
Loading 0:  45%|████▍     | 226/507 [00:06<00:11, 25.29it/s]
Loading 0:  45%|████▌     | 230/507 [00:07<00:10, 25.22it/s]
Loading 0:  46%|████▋     | 235/507 [00:07<00:09, 29.28it/s]
Loading 0:  47%|████▋     | 239/507 [00:07<00:09, 27.23it/s]
Loading 0:  49%|████▊     | 246/507 [00:07<00:07, 34.32it/s]
Loading 0:  49%|████▉     | 250/507 [00:07<00:07, 33.56it/s]
Loading 0:  50%|█████     | 255/507 [00:07<00:07, 35.52it/s]
Loading 0:  51%|█████     | 259/507 [00:07<00:07, 34.09it/s]
Loading 0:  52%|█████▏    | 264/507 [00:08<00:06, 36.51it/s]
Loading 0:  53%|█████▎    | 268/507 [00:08<00:06, 35.03it/s]
Loading 0:  54%|█████▍    | 273/507 [00:08<00:06, 36.47it/s]
Loading 0:  55%|█████▍    | 277/507 [00:08<00:06, 34.81it/s]
Loading 0:  56%|█████▌    | 283/507 [00:08<00:06, 36.33it/s]
Loading 0:  57%|█████▋    | 287/507 [00:08<00:09, 23.49it/s]
Loading 0:  58%|█████▊    | 293/507 [00:09<00:08, 26.74it/s]
Loading 0:  59%|█████▉    | 299/507 [00:23<00:07, 26.74it/s]
Loading 0:  59%|█████▉    | 300/507 [00:23<02:44,  1.26it/s]
Loading 0:  60%|█████▉    | 302/507 [00:23<02:23,  1.43it/s]
Loading 0:  61%|██████    | 307/507 [00:23<01:36,  2.06it/s]
Loading 0:  61%|██████    | 310/507 [00:24<01:16,  2.56it/s]
Loading 0:  62%|██████▏   | 314/507 [00:24<00:54,  3.51it/s]
Loading 0:  63%|██████▎   | 319/507 [00:24<00:36,  5.11it/s]
Loading 0:  64%|██████▎   | 323/507 [00:24<00:27,  6.75it/s]
Loading 0:  65%|██████▍   | 328/507 [00:24<00:19,  9.36it/s]
Loading 0:  65%|██████▌   | 332/507 [00:24<00:14, 11.79it/s]
Loading 0:  66%|██████▋   | 336/507 [00:24<00:11, 14.40it/s]
Loading 0:  67%|██████▋   | 340/507 [00:25<00:11, 14.14it/s]
Loading 0:  68%|██████▊   | 343/507 [00:25<00:10, 15.40it/s]
Loading 0:  68%|██████▊   | 347/507 [00:25<00:09, 17.63it/s]
Loading 0:  70%|██████▉   | 354/507 [00:25<00:05, 25.88it/s]
Loading 0:  71%|███████   | 358/507 [00:25<00:05, 28.02it/s]
Loading 0:  72%|███████▏  | 363/507 [00:25<00:04, 32.51it/s]
Loading 0:  73%|███████▎  | 368/507 [00:25<00:04, 34.45it/s]
Loading 0:  74%|███████▎  | 373/507 [00:25<00:03, 36.92it/s]
Loading 0:  75%|███████▍  | 378/507 [00:25<00:03, 39.25it/s]
Loading 0:  76%|███████▌  | 383/507 [00:26<00:03, 32.74it/s]
Loading 0:  77%|███████▋  | 389/507 [00:26<00:03, 38.01it/s]
Loading 0:  78%|███████▊  | 394/507 [00:26<00:03, 34.97it/s]
Loading 0:  79%|███████▊  | 398/507 [00:26<00:03, 29.75it/s]
Loading 0:  79%|███████▉  | 402/507 [00:26<00:03, 28.76it/s]
Loading 0:  80%|████████  | 408/507 [00:26<00:02, 34.07it/s]
Loading 0:  81%|████████▏ | 412/507 [00:27<00:02, 33.75it/s]
Loading 0:  82%|████████▏ | 417/507 [00:27<00:02, 35.89it/s]
Loading 0:  83%|████████▎ | 421/507 [00:27<00:02, 34.35it/s]
Loading 0:  84%|████████▍ | 427/507 [00:27<00:02, 37.97it/s]
Loading 0:  85%|████████▌ | 432/507 [00:27<00:01, 40.49it/s]
Loading 0:  86%|████████▌ | 437/507 [00:27<00:01, 35.73it/s]
Loading 0:  88%|████████▊ | 445/507 [00:27<00:01, 43.26it/s]
Loading 0:  89%|████████▉ | 451/507 [00:27<00:01, 42.63it/s]
Loading 0:  90%|████████▉ | 456/507 [00:30<00:06,  7.37it/s]
Loading 0:  91%|█████████ | 460/507 [00:30<00:05,  8.85it/s]
Loading 0:  92%|█████████▏| 465/507 [00:30<00:03, 11.21it/s]
Loading 0:  93%|█████████▎| 472/507 [00:30<00:02, 15.92it/s]
Loading 0:  94%|█████████▍| 476/507 [00:30<00:01, 17.71it/s]
Loading 0:  95%|█████████▍| 481/507 [00:30<00:01, 21.35it/s]
Loading 0:  96%|█████████▌| 485/507 [00:31<00:00, 22.95it/s]
Loading 0:  97%|█████████▋| 490/507 [00:31<00:00, 26.69it/s]
Loading 0:  97%|█████████▋| 494/507 [00:31<00:00, 28.11it/s]
Loading 0:  98%|█████████▊| 499/507 [00:31<00:00, 31.90it/s]
Loading 0:  99%|█████████▉| 503/507 [00:31<00:00, 32.53it/s]
                                                            
Job chaiml-espresso-ant-llam-1666-v4-mkmlizer completed after 122.2s with status: succeeded
Stopping job with name chaiml-espresso-ant-llam-1666-v4-mkmlizer
Pipeline stage MKMLizer completed in 125.99s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-espresso-ant-llam-1666-v4
Waiting for inference service chaiml-espresso-ant-llam-1666-v4 to be ready
Failed to get response for submission chaiml-lexical-viral-v5a_3966_v4: ('http://chaiml-lexical-viral-v5a-3966-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:38984->127.0.0.1:8080: read: connection reset by peer\n')
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-v4 ready after 174.54620265960693s
Pipeline stage MKMLDeployer completed in 175.91s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.768706798553467s
Received healthy response to inference request in 2.501901388168335s
Received healthy response to inference request in 2.386605978012085s
Received healthy response to inference request in 2.2866933345794678s
Received healthy response to inference request in 2.404942512512207s
5 requests
0 failed requests
5th percentile: 2.3066758632659914
10th percentile: 2.3266583919525146
20th percentile: 2.3666234493255613
30th percentile: 2.3902732849121096
40th percentile: 2.3976078987121583
50th percentile: 2.404942512512207
60th percentile: 2.443726062774658
70th percentile: 2.4825096130371094
80th percentile: 2.5552624702453612
90th percentile: 2.6619846343994142
95th percentile: 2.7153457164764405
99th percentile: 2.7580345821380616
mean time: 2.469770002365112
Pipeline stage StressChecker completed in 13.69s
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 2.75s
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 2.33s
Shutdown handler de-registered
chaiml-espresso-ant-llam_1666_v4 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 3186.15s
Shutdown handler de-registered
chaiml-espresso-ant-llam_1666_v4 status is now inactive due to auto deactivation removed underperforming models