chaiml-espresso-ant-lla_74988

developer_uid: azuruce

submission_id: chaiml-espresso-ant-lla_74988_v3

model_name: chaiml-espresso-ant-lla_74988_v3

model_group: ChaiML/espresso_ant_llam

status: torndown

timestamp: 2025-03-06T18:41:54+00:00

num_battles: 12558

num_wins: 5890

celo_rating: 1262.95

family_friendly_score: 0.5680000000000001

family_friendly_standard_error: 0.007005369369276684

submission_type: basic

model_repo: ChaiML/espresso_ant_llama_241204_albert_v2_sft_4epoch_128alpha

model_architecture: MistralForCausalLM

model_num_parameters: 22247282688.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.3717074260734217, 'latency_mean': 2.690194009542465, 'latency_p50': 2.706560730934143, 'latency_p90': 2.9511539936065674}, {'batch_size': 2, 'throughput': 0.5921936031598278, 'latency_mean': 3.374499098062515, 'latency_p50': 3.354556441307068, 'latency_p90': 3.7292573928833006}, {'batch_size': 3, 'throughput': 0.7389910222137789, 'latency_mean': 4.048295944929123, 'latency_p50': 4.0300527811050415, 'latency_p90': 4.445098900794983}, {'batch_size': 4, 'throughput': 0.8579726653417868, 'latency_mean': 4.636322997808456, 'latency_p50': 4.595293402671814, 'latency_p90': 5.144885897636414}, {'batch_size': 5, 'throughput': 0.9550793488117499, 'latency_mean': 5.227407982349396, 'latency_p50': 5.266003847122192, 'latency_p90': 5.722673082351685}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-espresso-ant-lla_74988_v3

is_internal_developer: False

language_model: ChaiML/espresso_ant_llama_241204_albert_v2_sft_4epoch_128alpha

model_size: 22B

ranking_group: single

throughput_3p7s: 0.67

us_pacific_date: 2025-03-06

win_ratio: 0.4690237298932951

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': ['<|eot_id|>', '<|end_of_text|>', 'You:', '\n'], '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-lla-74988-v3-mkmlizer
Waiting for job on chaiml-espresso-ant-lla-74988-v3-mkmlizer to finish
chaiml-espresso-ant-lla-74988-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-espresso-ant-lla-74988-v3-mkmlizer: ║     _____            __           __                                ║
chaiml-espresso-ant-lla-74988-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-espresso-ant-lla-74988-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-espresso-ant-lla-74988-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-espresso-ant-lla-74988-v3-mkmlizer: ║       /___/                                                         ║
chaiml-espresso-ant-lla-74988-v3-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-lla-74988-v3-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-espresso-ant-lla-74988-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-espresso-ant-lla-74988-v3-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-espresso-ant-lla-74988-v3-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-lla-74988-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-espresso-ant-lla-74988-v3-mkmlizer: ║  belonging to:                                                      ║
chaiml-espresso-ant-lla-74988-v3-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-lla-74988-v3-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-espresso-ant-lla-74988-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-espresso-ant-lla-74988-v3-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-espresso-ant-lla-74988-v3-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-lla-74988-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-espresso-ant-lla-74988-v3-mkmlizer: Downloaded to shared memory in 70.438s
chaiml-espresso-ant-lla-74988-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp0prboyx4, device:0
chaiml-espresso-ant-lla-74988-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-espresso-ant-lla-74988-v3-mkmlizer: quantized model in 42.505s
chaiml-espresso-ant-lla-74988-v3-mkmlizer: Processed model ChaiML/espresso_ant_llama_241204_albert_v2_sft_4epoch_128alpha in 112.944s
chaiml-espresso-ant-lla-74988-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-espresso-ant-lla-74988-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-espresso-ant-lla-74988-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-espresso-ant-lla-74988-v3
chaiml-espresso-ant-lla-74988-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-espresso-ant-lla-74988-v3/config.json
chaiml-espresso-ant-lla-74988-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-espresso-ant-lla-74988-v3/special_tokens_map.json
chaiml-espresso-ant-lla-74988-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-espresso-ant-lla-74988-v3/tokenizer_config.json
chaiml-espresso-ant-lla-74988-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-espresso-ant-lla-74988-v3/tokenizer.json
chaiml-espresso-ant-lla-74988-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-espresso-ant-lla-74988-v3/flywheel_model.1.safetensors
chaiml-espresso-ant-lla-74988-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-espresso-ant-lla-74988-v3/flywheel_model.0.safetensors
chaiml-espresso-ant-lla-74988-v3-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:17, 28.12it/s]
Loading 0:   2%|▏         | 12/507 [00:00<00:11, 44.77it/s]
Loading 0:   3%|▎         | 17/507 [00:00<00:11, 41.65it/s]
Loading 0:   4%|▍         | 22/507 [00:00<00:11, 41.76it/s]
Loading 0:   5%|▌         | 27/507 [00:00<00:11, 43.04it/s]
Loading 0:   6%|▋         | 32/507 [00:00<00:13, 36.26it/s]
Loading 0:   8%|▊         | 39/507 [00:00<00:10, 43.75it/s]
Loading 0:   9%|▊         | 44/507 [00:01<00:10, 43.21it/s]
Loading 0:  10%|▉         | 49/507 [00:01<00:12, 37.70it/s]
Loading 0:  11%|█         | 54/507 [00:01<00:15, 28.99it/s]
Loading 0:  11%|█▏        | 58/507 [00:01<00:15, 29.59it/s]
Loading 0:  12%|█▏        | 63/507 [00:01<00:13, 33.17it/s]
Loading 0:  13%|█▎        | 67/507 [00:01<00:13, 32.24it/s]
Loading 0:  14%|█▍        | 73/507 [00:02<00:12, 35.09it/s]
Loading 0:  16%|█▌        | 80/507 [00:02<00:11, 37.23it/s]
Loading 0:  17%|█▋        | 87/507 [00:02<00:09, 42.61it/s]
Loading 0:  18%|█▊        | 92/507 [00:02<00:10, 40.76it/s]
Loading 0:  19%|█▉        | 97/507 [00:02<00:10, 40.43it/s]
Loading 0:  20%|██        | 102/507 [00:02<00:09, 42.06it/s]
Loading 0:  21%|██        | 107/507 [00:02<00:11, 36.23it/s]
Loading 0:  22%|██▏       | 113/507 [00:03<00:12, 31.55it/s]
Loading 0:  23%|██▎       | 117/507 [00:03<00:13, 29.90it/s]
Loading 0:  24%|██▍       | 122/507 [00:03<00:12, 30.31it/s]
Loading 0:  25%|██▌       | 129/507 [00:03<00:10, 37.20it/s]
Loading 0:  26%|██▋       | 134/507 [00:03<00:09, 37.87it/s]
Loading 0:  27%|██▋       | 139/507 [00:03<00:09, 39.04it/s]
Loading 0:  28%|██▊       | 144/507 [00:03<00:09, 39.56it/s]
Loading 0:  29%|██▉       | 149/507 [00:04<00:10, 34.97it/s]
Loading 0:  31%|███       | 156/507 [00:04<00:08, 41.96it/s]
Loading 0:  32%|███▏      | 161/507 [00:04<00:08, 42.26it/s]
Loading 0:  33%|███▎      | 166/507 [00:04<00:07, 43.83it/s]
Loading 0:  34%|███▎      | 171/507 [00:04<00:12, 27.30it/s]
Loading 0:  35%|███▍      | 176/507 [00:04<00:11, 29.33it/s]
Loading 0:  36%|███▌      | 183/507 [00:05<00:08, 36.71it/s]
Loading 0:  37%|███▋      | 188/507 [00:05<00:08, 37.57it/s]
Loading 0:  38%|███▊      | 193/507 [00:05<00:08, 38.70it/s]
Loading 0:  39%|███▉      | 198/507 [00:05<00:07, 40.24it/s]
Loading 0:  40%|████      | 203/507 [00:05<00:08, 35.54it/s]
Loading 0:  41%|████▏     | 210/507 [00:05<00:06, 43.13it/s]
Loading 0:  42%|████▏     | 215/507 [00:05<00:06, 42.90it/s]
Loading 0:  43%|████▎     | 220/507 [00:05<00:07, 38.00it/s]
Loading 0:  44%|████▍     | 225/507 [00:06<00:09, 28.99it/s]
Loading 0:  45%|████▌     | 230/507 [00:06<00:09, 29.62it/s]
Loading 0:  47%|████▋     | 237/507 [00:06<00:07, 35.44it/s]
Loading 0:  48%|████▊     | 241/507 [00:06<00:07, 34.62it/s]
Loading 0:  49%|████▊     | 246/507 [00:06<00:07, 36.45it/s]
Loading 0:  49%|████▉     | 250/507 [00:06<00:07, 35.26it/s]
Loading 0:  50%|█████     | 255/507 [00:06<00:06, 37.61it/s]
Loading 0:  51%|█████     | 259/507 [00:07<00:06, 36.44it/s]
Loading 0:  52%|█████▏    | 264/507 [00:07<00:06, 38.59it/s]
Loading 0:  53%|█████▎    | 268/507 [00:07<00:07, 34.08it/s]
Loading 0:  54%|█████▍    | 273/507 [00:07<00:06, 35.94it/s]
Loading 0:  55%|█████▍    | 277/507 [00:07<00:06, 34.54it/s]
Loading 0:  56%|█████▌    | 283/507 [00:07<00:05, 37.51it/s]
Loading 0:  57%|█████▋    | 287/507 [00:08<00:08, 24.76it/s]
Loading 0:  58%|█████▊    | 293/507 [00:08<00:07, 28.24it/s]
Loading 0:  59%|█████▉    | 299/507 [00:22<00:07, 28.24it/s]
Loading 0:  59%|█████▉    | 300/507 [00:22<02:43,  1.26it/s]
Loading 0:  60%|█████▉    | 302/507 [00:22<02:23,  1.43it/s]
Loading 0:  61%|██████    | 307/507 [00:23<01:37,  2.06it/s]
Loading 0:  61%|██████    | 310/507 [00:23<01:16,  2.56it/s]
Loading 0:  62%|██████▏   | 314/507 [00:23<00:54,  3.52it/s]
Loading 0:  63%|██████▎   | 318/507 [00:23<00:39,  4.80it/s]
Loading 0:  64%|██████▎   | 322/507 [00:23<00:28,  6.43it/s]
Loading 0:  64%|██████▍   | 327/507 [00:23<00:19,  9.10it/s]
Loading 0:  65%|██████▌   | 331/507 [00:23<00:15, 11.48it/s]
Loading 0:  66%|██████▋   | 336/507 [00:23<00:11, 15.46it/s]
Loading 0:  67%|██████▋   | 340/507 [00:24<00:10, 15.96it/s]
Loading 0:  68%|██████▊   | 344/507 [00:24<00:08, 18.56it/s]
Loading 0:  69%|██████▊   | 348/507 [00:24<00:07, 20.55it/s]
Loading 0:  70%|██████▉   | 354/507 [00:24<00:05, 27.03it/s]
Loading 0:  71%|███████   | 358/507 [00:24<00:05, 28.85it/s]
Loading 0:  72%|███████▏  | 363/507 [00:24<00:04, 33.27it/s]
Loading 0:  73%|███████▎  | 368/507 [00:24<00:04, 33.99it/s]
Loading 0:  74%|███████▎  | 373/507 [00:24<00:03, 35.66it/s]
Loading 0:  75%|███████▍  | 378/507 [00:25<00:03, 38.27it/s]
Loading 0:  76%|███████▌  | 383/507 [00:25<00:03, 33.73it/s]
Loading 0:  77%|███████▋  | 389/507 [00:25<00:02, 39.45it/s]
Loading 0:  78%|███████▊  | 394/507 [00:25<00:03, 36.87it/s]
Loading 0:  79%|███████▊  | 398/507 [00:25<00:03, 31.17it/s]
Loading 0:  79%|███████▉  | 402/507 [00:25<00:03, 29.87it/s]
Loading 0:  80%|████████  | 408/507 [00:25<00:02, 35.07it/s]
Loading 0:  81%|████████▏ | 412/507 [00:26<00:02, 34.98it/s]
Loading 0:  82%|████████▏ | 417/507 [00:26<00:02, 38.12it/s]
Loading 0:  83%|████████▎ | 421/507 [00:26<00:02, 37.42it/s]
Loading 0:  84%|████████▍ | 426/507 [00:26<00:02, 40.49it/s]
Loading 0:  85%|████████▌ | 431/507 [00:26<00:01, 39.41it/s]
Loading 0:  86%|████████▌ | 436/507 [00:26<00:01, 40.05it/s]
Loading 0:  87%|████████▋ | 441/507 [00:26<00:01, 42.11it/s]
Loading 0:  88%|████████▊ | 446/507 [00:26<00:01, 35.25it/s]
Loading 0:  90%|████████▉ | 454/507 [00:27<00:01, 42.04it/s]
Loading 0:  91%|█████████ | 459/507 [00:29<00:06,  7.00it/s]
Loading 0:  92%|█████████▏| 465/507 [00:29<00:04,  9.44it/s]
Loading 0:  93%|█████████▎| 472/507 [00:29<00:02, 13.25it/s]
Loading 0:  94%|█████████▍| 477/507 [00:29<00:01, 15.95it/s]
Loading 0:  95%|█████████▌| 482/507 [00:29<00:01, 19.21it/s]
Loading 0:  96%|█████████▌| 487/507 [00:30<00:00, 23.00it/s]
Loading 0:  97%|█████████▋| 492/507 [00:30<00:00, 23.72it/s]
Loading 0:  98%|█████████▊| 499/507 [00:30<00:00, 30.25it/s]
Loading 0:  99%|█████████▉| 504/507 [00:30<00:00, 32.08it/s]
                                                            
Job chaiml-espresso-ant-lla-74988-v3-mkmlizer completed after 144.39s with status: succeeded
Stopping job with name chaiml-espresso-ant-lla-74988-v3-mkmlizer
Pipeline stage MKMLizer completed in 144.91s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-espresso-ant-lla-74988-v3
Waiting for inference service chaiml-espresso-ant-lla-74988-v3 to be ready
Inference service chaiml-espresso-ant-lla-74988-v3 ready after 100.35044050216675s
Pipeline stage MKMLDeployer completed in 100.87s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.146367311477661s
Received healthy response to inference request in 2.462289571762085s
Received healthy response to inference request in 2.3639957904815674s
Received healthy response to inference request in 2.47831130027771s
Received healthy response to inference request in 2.5233707427978516s
5 requests
0 failed requests
5th percentile: 2.383654546737671
10th percentile: 2.4033133029937743
20th percentile: 2.4426308155059813
30th percentile: 2.46549391746521
40th percentile: 2.47190260887146
50th percentile: 2.47831130027771
60th percentile: 2.4963350772857664
70th percentile: 2.5143588542938233
80th percentile: 2.6479700565338136
90th percentile: 2.897168684005737
95th percentile: 3.021767997741699
99th percentile: 3.1214474487304686
mean time: 2.594866943359375
Pipeline stage StressChecker completed in 14.42s
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 0.77s
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 0.65s
Shutdown handler de-registered
chaiml-espresso-ant-lla_74988_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5347.44s
Shutdown handler de-registered
chaiml-espresso-ant-lla_74988_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-espresso-ant-lla_74988_v3 status is now torndown due to DeploymentManager action