chaiml-espresso-ant-llam_1666

developer_uid: azuruce

submission_id: chaiml-espresso-ant-llam_1666_v1

model_name: chaiml-espresso-ant-llam_1666_v1

model_group: ChaiML/espresso_ant_llam

status: inactive

timestamp: 2024-12-05T05:52:40+00:00

num_battles: 9166

num_wins: 4887

celo_rating: 1282.32

family_friendly_score: 0.5826

family_friendly_standard_error: 0.006973911958148023

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: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.3776249115355764, 'latency_mean': 2.6480563271045683, 'latency_p50': 2.6319539546966553, 'latency_p90': 2.927074146270752}, {'batch_size': 2, 'throughput': 0.5987991680401394, 'latency_mean': 3.326946595907211, 'latency_p50': 3.3379474878311157, 'latency_p90': 3.6802845001220703}, {'batch_size': 3, 'throughput': 0.7638317761978272, 'latency_mean': 3.9111162781715394, 'latency_p50': 3.9252398014068604, 'latency_p90': 4.278369736671448}, {'batch_size': 4, 'throughput': 0.8875551274833766, 'latency_mean': 4.493686618804932, 'latency_p50': 4.510318636894226, 'latency_p90': 5.03209855556488}, {'batch_size': 5, 'throughput': 0.9798470512611228, 'latency_mean': 5.069052325487137, 'latency_p50': 5.051960468292236, 'latency_p90': 5.5811409711837765}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-espresso-ant-llam_1666_v1

is_internal_developer: True

language_model: ChaiML/espresso_ant_llama_241204_albert_v2_sft_2epoch_128alpha

model_size: 22B

ranking_group: single

throughput_3p7s: 0.71

us_pacific_date: 2024-12-04

win_ratio: 0.5331660484398866

generation_params: {'temperature': 0.9, '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-1666-v1-mkmlizer
Waiting for job on chaiml-espresso-ant-llam-1666-v1-mkmlizer to finish
chaiml-espresso-ant-llam-1666-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-espresso-ant-llam-1666-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-espresso-ant-llam-1666-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-espresso-ant-llam-1666-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-espresso-ant-llam-1666-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-espresso-ant-llam-1666-v1-mkmlizer: ║       /___/                                                         ║
chaiml-espresso-ant-llam-1666-v1-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-llam-1666-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-espresso-ant-llam-1666-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-espresso-ant-llam-1666-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-espresso-ant-llam-1666-v1-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-llam-1666-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-espresso-ant-llam-1666-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-espresso-ant-llam-1666-v1-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-llam-1666-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-espresso-ant-llam-1666-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-espresso-ant-llam-1666-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-espresso-ant-llam-1666-v1-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-llam-1666-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-espresso-ant-llam-1666-v1-mkmlizer: Downloaded to shared memory in 70.880s
chaiml-espresso-ant-llam-1666-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpao31a9uv, device:0
chaiml-espresso-ant-llam-1666-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-espresso-ant-llam-1666-v1-mkmlizer: quantized model in 50.533s
chaiml-espresso-ant-llam-1666-v1-mkmlizer: Processed model ChaiML/espresso_ant_llama_241204_albert_v2_sft_2epoch_128alpha in 121.413s
chaiml-espresso-ant-llam-1666-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-espresso-ant-llam-1666-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-espresso-ant-llam-1666-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v1
chaiml-espresso-ant-llam-1666-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v1/special_tokens_map.json
chaiml-espresso-ant-llam-1666-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v1/config.json
chaiml-espresso-ant-llam-1666-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v1/tokenizer_config.json
chaiml-espresso-ant-llam-1666-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v1/tokenizer.json
chaiml-espresso-ant-llam-1666-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v1/flywheel_model.1.safetensors
chaiml-espresso-ant-llam-1666-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v1/flywheel_model.0.safetensors
chaiml-espresso-ant-llam-1666-v1-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   0%|          | 2/507 [00:00<01:12,  6.92it/s]
Loading 0:   1%|          | 5/507 [00:00<01:12,  6.89it/s]
Loading 0:   2%|▏         | 12/507 [00:00<00:32, 15.04it/s]
Loading 0:   3%|▎         | 14/507 [00:01<00:54,  9.00it/s]
Loading 0:   4%|▍         | 21/507 [00:01<00:29, 16.29it/s]
Loading 0:   5%|▍         | 24/507 [00:02<00:49,  9.80it/s]
Loading 0:   6%|▌         | 30/507 [00:02<00:35, 13.26it/s]
Loading 0:   7%|▋         | 33/507 [00:02<00:31, 14.98it/s]
Loading 0:   8%|▊         | 39/507 [00:02<00:22, 20.99it/s]
Loading 0:   8%|▊         | 43/507 [00:02<00:19, 23.82it/s]
Loading 0:   9%|▉         | 48/507 [00:03<00:18, 25.19it/s]
Loading 0:  10%|█         | 53/507 [00:03<00:19, 23.36it/s]
Loading 0:  11%|█         | 56/507 [00:04<00:43, 10.39it/s]
Loading 0:  12%|█▏        | 63/507 [00:04<00:28, 15.61it/s]
Loading 0:  13%|█▎        | 67/507 [00:04<00:24, 18.19it/s]
Loading 0:  14%|█▍        | 72/507 [00:04<00:19, 22.37it/s]
Loading 0:  15%|█▌        | 78/507 [00:04<00:15, 28.24it/s]
Loading 0:  16%|█▋        | 83/507 [00:04<00:13, 30.65it/s]
Loading 0:  17%|█▋        | 88/507 [00:04<00:12, 32.97it/s]
Loading 0:  18%|█▊        | 93/507 [00:04<00:11, 36.06it/s]
Loading 0:  19%|█▉        | 98/507 [00:05<00:12, 32.26it/s]
Loading 0:  21%|██        | 105/507 [00:05<00:10, 39.35it/s]
Loading 0:  22%|██▏       | 110/507 [00:05<00:22, 18.04it/s]
Loading 0:  22%|██▏       | 114/507 [00:07<00:55,  7.14it/s]
Loading 0:  23%|██▎       | 117/507 [00:07<00:51,  7.54it/s]
Loading 0:  24%|██▍       | 121/507 [00:08<00:50,  7.60it/s]
Loading 0:  24%|██▍       | 123/507 [00:08<00:56,  6.80it/s]
Loading 0:  25%|██▌       | 129/507 [00:08<00:35, 10.57it/s]
Loading 0:  26%|██▌       | 132/507 [00:09<00:30, 12.33it/s]
Loading 0:  27%|██▋       | 138/507 [00:09<00:20, 17.66it/s]
Loading 0:  28%|██▊       | 142/507 [00:09<00:17, 20.33it/s]
Loading 0:  29%|██▉       | 147/507 [00:09<00:17, 20.29it/s]
Loading 0:  30%|██▉       | 150/507 [00:10<00:33, 10.73it/s]
Loading 0:  31%|███       | 156/507 [00:10<00:22, 15.32it/s]
Loading 0:  31%|███▏      | 159/507 [00:10<00:20, 16.68it/s]
Loading 0:  32%|███▏      | 164/507 [00:10<00:15, 21.55it/s]
Loading 0:  33%|███▎      | 169/507 [00:10<00:15, 21.83it/s]
Loading 0:  34%|███▍      | 173/507 [00:11<00:13, 24.05it/s]
Loading 0:  35%|███▍      | 177/507 [00:11<00:12, 25.40it/s]
Loading 0:  36%|███▌      | 183/507 [00:11<00:10, 31.97it/s]
Loading 0:  37%|███▋      | 187/507 [00:11<00:09, 32.94it/s]
Loading 0:  38%|███▊      | 192/507 [00:11<00:08, 36.84it/s]
Loading 0:  39%|███▉      | 197/507 [00:11<00:08, 37.77it/s]
Loading 0:  40%|███▉      | 202/507 [00:11<00:07, 39.37it/s]
Loading 0:  41%|████      | 208/507 [00:11<00:07, 40.10it/s]
Loading 0:  42%|████▏     | 213/507 [00:11<00:07, 39.38it/s]
Loading 0:  43%|████▎     | 218/507 [00:12<00:06, 41.72it/s]
Loading 0:  44%|████▍     | 223/507 [00:12<00:07, 38.48it/s]
Loading 0:  45%|████▍     | 227/507 [00:12<00:08, 32.54it/s]
Loading 0:  46%|████▌     | 231/507 [00:12<00:09, 30.52it/s]
Loading 0:  47%|████▋     | 237/507 [00:12<00:07, 35.84it/s]
Loading 0:  48%|████▊     | 241/507 [00:12<00:07, 36.03it/s]
Loading 0:  49%|████▊     | 246/507 [00:12<00:06, 38.65it/s]
Loading 0:  50%|████▉     | 251/507 [00:13<00:06, 38.72it/s]
Loading 0:  50%|█████     | 256/507 [00:13<00:06, 39.21it/s]
Loading 0:  51%|█████▏    | 261/507 [00:13<00:05, 41.36it/s]
Loading 0:  52%|█████▏    | 266/507 [00:13<00:06, 35.44it/s]
Loading 0:  54%|█████▍    | 273/507 [00:13<00:05, 42.15it/s]
Loading 0:  55%|█████▍    | 278/507 [00:13<00:05, 41.61it/s]
Loading 0:  56%|█████▌    | 283/507 [00:13<00:05, 41.76it/s]
Loading 0:  57%|█████▋    | 288/507 [00:14<00:07, 28.79it/s]
Loading 0:  58%|█████▊    | 293/507 [00:14<00:07, 29.37it/s]
Loading 0:  59%|█████▉    | 300/507 [00:28<02:43,  1.27it/s]
Loading 0:  60%|█████▉    | 302/507 [00:28<02:22,  1.44it/s]
Loading 0:  61%|██████    | 307/507 [00:29<01:36,  2.07it/s]
Loading 0:  61%|██████    | 310/507 [00:30<01:35,  2.07it/s]
Loading 0:  62%|██████▏   | 313/507 [00:30<01:13,  2.64it/s]
Loading 0:  63%|██████▎   | 319/507 [00:30<00:44,  4.26it/s]
Loading 0:  64%|██████▍   | 325/507 [00:30<00:28,  6.32it/s]
Loading 0:  65%|██████▍   | 329/507 [00:31<00:22,  7.95it/s]
Loading 0:  66%|██████▌   | 335/507 [00:31<00:15, 11.46it/s]
Loading 0:  67%|██████▋   | 340/507 [00:31<00:12, 13.48it/s]
Loading 0:  68%|██████▊   | 344/507 [00:31<00:10, 15.80it/s]
Loading 0:  69%|██████▊   | 348/507 [00:31<00:08, 17.86it/s]
Loading 0:  70%|██████▉   | 354/507 [00:31<00:06, 23.75it/s]
Loading 0:  71%|███████   | 358/507 [00:31<00:05, 26.04it/s]
Loading 0:  72%|███████▏  | 363/507 [00:32<00:04, 30.59it/s]
Loading 0:  73%|███████▎  | 368/507 [00:32<00:04, 33.04it/s]
Loading 0:  74%|███████▎  | 373/507 [00:32<00:03, 35.79it/s]
Loading 0:  75%|███████▍  | 379/507 [00:32<00:03, 37.56it/s]
Loading 0:  76%|███████▌  | 384/507 [00:32<00:03, 37.80it/s]
Loading 0:  77%|███████▋  | 390/507 [00:32<00:03, 36.73it/s]
Loading 0:  78%|███████▊  | 395/507 [00:32<00:03, 31.06it/s]
Loading 0:  79%|███████▉  | 401/507 [00:33<00:03, 30.48it/s]
Loading 0:  80%|████████  | 408/507 [00:33<00:02, 36.80it/s]
Loading 0:  81%|████████▏ | 413/507 [00:33<00:02, 37.40it/s]
Loading 0:  82%|████████▏ | 418/507 [00:33<00:02, 38.01it/s]
Loading 0:  83%|████████▎ | 423/507 [00:33<00:02, 40.13it/s]
Loading 0:  84%|████████▍ | 428/507 [00:33<00:02, 34.93it/s]
Loading 0:  86%|████████▌ | 435/507 [00:33<00:01, 41.78it/s]
Loading 0:  87%|████████▋ | 440/507 [00:34<00:01, 41.97it/s]
Loading 0:  88%|████████▊ | 445/507 [00:34<00:01, 41.30it/s]
Loading 0:  89%|████████▉ | 451/507 [00:34<00:01, 41.16it/s]
Loading 0:  90%|████████▉ | 456/507 [00:36<00:07,  6.98it/s]
Loading 0:  91%|█████████ | 460/507 [00:36<00:05,  8.45it/s]
Loading 0:  92%|█████████▏| 465/507 [00:36<00:03, 10.81it/s]
Loading 0:  93%|█████████▎| 472/507 [00:36<00:02, 15.44it/s]
Loading 0:  94%|█████████▍| 476/507 [00:37<00:01, 17.80it/s]
Loading 0:  95%|█████████▍| 481/507 [00:37<00:01, 21.48it/s]
Loading 0:  96%|█████████▌| 485/507 [00:37<00:00, 23.64it/s]
Loading 0:  97%|█████████▋| 490/507 [00:37<00:00, 27.37it/s]
Loading 0:  97%|█████████▋| 494/507 [00:37<00:00, 28.98it/s]
Loading 0:  98%|█████████▊| 499/507 [00:37<00:00, 32.86it/s]
Loading 0:  99%|█████████▉| 503/507 [00:37<00:00, 33.63it/s]
                                                            
Job chaiml-espresso-ant-llam-1666-v1-mkmlizer completed after 155.24s with status: succeeded
Stopping job with name chaiml-espresso-ant-llam-1666-v1-mkmlizer
Pipeline stage MKMLizer completed in 156.37s
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-v1
Waiting for inference service chaiml-espresso-ant-llam-1666-v1 to be ready
Inference service chaiml-espresso-ant-llam-1666-v1 ready after 175.5771050453186s
Pipeline stage MKMLDeployer completed in 177.05s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.867905378341675s
Received healthy response to inference request in 2.427882194519043s
Received healthy response to inference request in 2.4923977851867676s
Received healthy response to inference request in 2.371293067932129s
Received healthy response to inference request in 2.471298933029175s
5 requests
0 failed requests
5th percentile: 2.382610893249512
10th percentile: 2.3939287185668947
20th percentile: 2.41656436920166
30th percentile: 2.4365655422210692
40th percentile: 2.4539322376251222
50th percentile: 2.471298933029175
60th percentile: 2.479738473892212
70th percentile: 2.488178014755249
80th percentile: 2.567499303817749
90th percentile: 2.717702341079712
95th percentile: 2.7928038597106934
99th percentile: 2.8528850746154784
mean time: 2.526155471801758
Pipeline stage StressChecker completed in 14.06s
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 2.22s
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 2.04s
Shutdown handler de-registered
chaiml-espresso-ant-llam_1666_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 0.10s
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-espresso-ant-llam-1666-v1-profiler
Waiting for inference service chaiml-espresso-ant-llam-1666-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 3281.22s
Shutdown handler de-registered
chaiml-espresso-ant-llam_1666_v1 status is now inactive due to auto deactivation removed underperforming models