chaiml-small-espresso-an_7267

developer_uid: azuruce

submission_id: chaiml-small-espresso-an_7267_v2

model_name: chaiml-small-espresso-an_7267_v2

model_group: ChaiML/small_espresso_an

status: inactive

timestamp: 2024-12-06T23:49:17+00:00

num_battles: 10862

num_wins: 5360

celo_rating: 1256.4

family_friendly_score: 0.569

family_friendly_standard_error: 0.007003413453452538

submission_type: basic

model_repo: ChaiML/small_espresso_ant_llama_story_241205_albert_ez_v1_sft-3e128a

model_architecture: MistralForCausalLM

model_num_parameters: 22247282688.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.3838577569676507, 'latency_mean': 2.6050494015216827, 'latency_p50': 2.6086983680725098, 'latency_p90': 2.876681756973267}, {'batch_size': 3, 'throughput': 0.8100210956576721, 'latency_mean': 3.6864048993587493, 'latency_p50': 3.70892071723938, 'latency_p90': 4.121573376655578}, {'batch_size': 5, 'throughput': 1.0811348127454277, 'latency_mean': 4.607005549669266, 'latency_p50': 4.598320126533508, 'latency_p90': 5.123002314567565}, {'batch_size': 6, 'throughput': 1.1607833069982758, 'latency_mean': 5.129126583337784, 'latency_p50': 5.086698651313782, 'latency_p90': 5.707319641113281}, {'batch_size': 10, 'throughput': 1.3665062511989459, 'latency_mean': 7.237203608751297, 'latency_p50': 7.239011645317078, 'latency_p90': 8.136486291885376}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-small-espresso-an_7267_v2

is_internal_developer: True

language_model: ChaiML/small_espresso_ant_llama_story_241205_albert_ez_v1_sft-3e128a

model_size: 22B

ranking_group: single

throughput_3p7s: 0.82

us_pacific_date: 2024-12-06

win_ratio: 0.49346345056159086

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-small-espresso-an-7267-v2-mkmlizer
Waiting for job on chaiml-small-espresso-an-7267-v2-mkmlizer to finish
chaiml-small-espresso-an-7267-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-small-espresso-an-7267-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-small-espresso-an-7267-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-small-espresso-an-7267-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-small-espresso-an-7267-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-small-espresso-an-7267-v2-mkmlizer: ║       /___/                                                         ║
chaiml-small-espresso-an-7267-v2-mkmlizer: ║                                                                     ║
chaiml-small-espresso-an-7267-v2-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-small-espresso-an-7267-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-small-espresso-an-7267-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-small-espresso-an-7267-v2-mkmlizer: ║                                                                     ║
chaiml-small-espresso-an-7267-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-small-espresso-an-7267-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-small-espresso-an-7267-v2-mkmlizer: ║                                                                     ║
chaiml-small-espresso-an-7267-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-small-espresso-an-7267-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-small-espresso-an-7267-v2-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-small-espresso-an-7267-v2-mkmlizer: ║                                                                     ║
chaiml-small-espresso-an-7267-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-small-espresso-an-7267-v2-mkmlizer: Downloaded to shared memory in 57.736s
chaiml-small-espresso-an-7267-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp3i9dxb1o, device:0
chaiml-small-espresso-an-7267-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-small-espresso-an-7267-v2-mkmlizer: quantized model in 43.886s
chaiml-small-espresso-an-7267-v2-mkmlizer: Processed model ChaiML/small_espresso_ant_llama_story_241205_albert_ez_v1_sft-3e128a in 101.623s
chaiml-small-espresso-an-7267-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-small-espresso-an-7267-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-small-espresso-an-7267-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-small-espresso-an-7267-v2
chaiml-small-espresso-an-7267-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-small-espresso-an-7267-v2/config.json
chaiml-small-espresso-an-7267-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-small-espresso-an-7267-v2/special_tokens_map.json
chaiml-small-espresso-an-7267-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-small-espresso-an-7267-v2/tokenizer_config.json
chaiml-small-espresso-an-7267-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-small-espresso-an-7267-v2/tokenizer.json
chaiml-small-espresso-an-7267-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-small-espresso-an-7267-v2/flywheel_model.1.safetensors
chaiml-small-espresso-an-7267-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-small-espresso-an-7267-v2/flywheel_model.0.safetensors
chaiml-small-espresso-an-7267-v2-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:21, 23.01it/s]
Loading 0:   2%|▏         | 12/507 [00:00<00:13, 37.45it/s]
Loading 0:   3%|▎         | 17/507 [00:00<00:13, 36.21it/s]
Loading 0:   4%|▍         | 21/507 [00:00<00:13, 37.18it/s]
Loading 0:   5%|▍         | 25/507 [00:00<00:13, 35.33it/s]
Loading 0:   6%|▌         | 30/507 [00:00<00:12, 36.95it/s]
Loading 0:   7%|▋         | 34/507 [00:00<00:13, 34.24it/s]
Loading 0:   8%|▊         | 39/507 [00:01<00:13, 35.99it/s]
Loading 0:   8%|▊         | 43/507 [00:01<00:13, 34.73it/s]
Loading 0:   9%|▉         | 47/507 [00:01<00:13, 34.75it/s]
Loading 0:  10%|█         | 51/507 [00:01<00:13, 33.90it/s]
Loading 0:  11%|█         | 55/507 [00:01<00:20, 21.93it/s]
Loading 0:  12%|█▏        | 59/507 [00:01<00:18, 24.73it/s]
Loading 0:  12%|█▏        | 63/507 [00:02<00:16, 27.27it/s]
Loading 0:  13%|█▎        | 67/507 [00:02<00:15, 28.31it/s]
Loading 0:  14%|█▍        | 72/507 [00:02<00:13, 32.77it/s]
Loading 0:  15%|█▌        | 78/507 [00:02<00:11, 37.71it/s]
Loading 0:  16%|█▋        | 83/507 [00:02<00:11, 36.15it/s]
Loading 0:  17%|█▋        | 87/507 [00:02<00:12, 34.88it/s]
Loading 0:  18%|█▊        | 91/507 [00:02<00:12, 33.67it/s]
Loading 0:  19%|█▉        | 96/507 [00:02<00:11, 35.38it/s]
Loading 0:  20%|█▉        | 100/507 [00:03<00:11, 34.10it/s]
Loading 0:  21%|██        | 105/507 [00:03<00:11, 35.27it/s]
Loading 0:  21%|██▏       | 109/507 [00:03<00:12, 32.98it/s]
Loading 0:  22%|██▏       | 113/507 [00:03<00:16, 23.82it/s]
Loading 0:  23%|██▎       | 116/507 [00:03<00:17, 22.77it/s]
Loading 0:  24%|██▍       | 122/507 [00:03<00:14, 26.90it/s]
Loading 0:  25%|██▌       | 129/507 [00:04<00:11, 33.80it/s]
Loading 0:  26%|██▌       | 133/507 [00:04<00:11, 32.75it/s]
Loading 0:  27%|██▋       | 138/507 [00:04<00:10, 35.22it/s]
Loading 0:  28%|██▊       | 142/507 [00:04<00:10, 34.30it/s]
Loading 0:  29%|██▉       | 147/507 [00:04<00:09, 36.91it/s]
Loading 0:  30%|██▉       | 151/507 [00:04<00:10, 35.23it/s]
Loading 0:  31%|███       | 156/507 [00:04<00:09, 37.86it/s]
Loading 0:  32%|███▏      | 160/507 [00:04<00:09, 35.91it/s]
Loading 0:  32%|███▏      | 164/507 [00:05<00:09, 34.70it/s]
Loading 0:  33%|███▎      | 169/507 [00:05<00:12, 27.09it/s]
Loading 0:  34%|███▍      | 173/507 [00:05<00:11, 28.61it/s]
Loading 0:  35%|███▍      | 177/507 [00:05<00:11, 28.44it/s]
Loading 0:  36%|███▌      | 183/507 [00:05<00:09, 34.09it/s]
Loading 0:  37%|███▋      | 187/507 [00:05<00:09, 34.05it/s]
Loading 0:  38%|███▊      | 192/507 [00:05<00:08, 37.20it/s]
Loading 0:  39%|███▊      | 196/507 [00:06<00:08, 36.39it/s]
Loading 0:  40%|███▉      | 201/507 [00:06<00:08, 38.12it/s]
Loading 0:  40%|████      | 205/507 [00:06<00:08, 37.62it/s]
Loading 0:  41%|████▏     | 210/507 [00:06<00:07, 40.14it/s]
Loading 0:  42%|████▏     | 215/507 [00:06<00:07, 37.94it/s]
Loading 0:  43%|████▎     | 219/507 [00:06<00:09, 31.34it/s]
Loading 0:  44%|████▍     | 224/507 [00:06<00:10, 26.68it/s]
Loading 0:  45%|████▌     | 229/507 [00:07<00:08, 31.18it/s]
Loading 0:  46%|████▌     | 233/507 [00:07<00:08, 32.52it/s]
Loading 0:  47%|████▋     | 237/507 [00:07<00:07, 33.81it/s]
Loading 0:  48%|████▊     | 241/507 [00:07<00:07, 33.26it/s]
Loading 0:  49%|████▊     | 246/507 [00:07<00:07, 35.91it/s]
Loading 0:  49%|████▉     | 250/507 [00:07<00:07, 34.98it/s]
Loading 0:  50%|█████     | 255/507 [00:07<00:06, 37.30it/s]
Loading 0:  51%|█████     | 259/507 [00:07<00:06, 36.07it/s]
Loading 0:  52%|█████▏    | 264/507 [00:07<00:06, 38.50it/s]
Loading 0:  53%|█████▎    | 268/507 [00:08<00:06, 36.92it/s]
Loading 0:  54%|█████▍    | 273/507 [00:08<00:05, 39.25it/s]
Loading 0:  55%|█████▍    | 277/507 [00:08<00:06, 37.56it/s]
Loading 0:  56%|█████▌    | 283/507 [00:08<00:05, 38.70it/s]
Loading 0:  57%|█████▋    | 287/507 [00:08<00:08, 25.62it/s]
Loading 0:  58%|█████▊    | 293/507 [00:08<00:07, 28.15it/s]
Loading 0:  59%|█████▉    | 299/507 [00:23<00:07, 28.15it/s]
Loading 0:  59%|█████▉    | 300/507 [00:23<02:45,  1.25it/s]
Loading 0:  60%|█████▉    | 302/507 [00:23<02:24,  1.42it/s]
Loading 0:  61%|██████    | 307/507 [00:23<01:37,  2.05it/s]
Loading 0:  61%|██████    | 310/507 [00:23<01:17,  2.54it/s]
Loading 0:  62%|██████▏   | 314/507 [00:24<00:55,  3.49it/s]
Loading 0:  63%|██████▎   | 319/507 [00:24<00:37,  5.07it/s]
Loading 0:  64%|██████▍   | 324/507 [00:24<00:25,  7.16it/s]
Loading 0:  65%|██████▍   | 328/507 [00:24<00:19,  9.14it/s]
Loading 0:  65%|██████▌   | 332/507 [00:24<00:15, 11.56it/s]
Loading 0:  66%|██████▋   | 336/507 [00:24<00:11, 14.50it/s]
Loading 0:  67%|██████▋   | 340/507 [00:24<00:11, 15.18it/s]
Loading 0:  68%|██████▊   | 344/507 [00:24<00:09, 17.83it/s]
Loading 0:  69%|██████▊   | 348/507 [00:25<00:08, 19.26it/s]
Loading 0:  70%|██████▉   | 354/507 [00:25<00:06, 25.17it/s]
Loading 0:  71%|███████   | 358/507 [00:25<00:05, 26.16it/s]
Loading 0:  72%|███████▏  | 363/507 [00:25<00:04, 29.64it/s]
Loading 0:  72%|███████▏  | 367/507 [00:25<00:04, 30.13it/s]
Loading 0:  73%|███████▎  | 372/507 [00:25<00:04, 33.75it/s]
Loading 0:  74%|███████▍  | 376/507 [00:25<00:03, 33.84it/s]
Loading 0:  75%|███████▌  | 381/507 [00:26<00:03, 36.86it/s]
Loading 0:  76%|███████▌  | 385/507 [00:26<00:03, 36.15it/s]
Loading 0:  77%|███████▋  | 389/507 [00:26<00:03, 36.33it/s]
Loading 0:  78%|███████▊  | 393/507 [00:26<00:03, 35.70it/s]
Loading 0:  78%|███████▊  | 397/507 [00:26<00:04, 25.07it/s]
Loading 0:  79%|███████▉  | 401/507 [00:26<00:04, 25.75it/s]
Loading 0:  80%|████████  | 406/507 [00:26<00:03, 30.79it/s]
Loading 0:  81%|████████  | 410/507 [00:27<00:03, 29.36it/s]
Loading 0:  82%|████████▏ | 417/507 [00:27<00:02, 36.73it/s]
Loading 0:  83%|████████▎ | 421/507 [00:27<00:02, 35.92it/s]
Loading 0:  84%|████████▍ | 426/507 [00:27<00:02, 38.14it/s]
Loading 0:  85%|████████▍ | 430/507 [00:27<00:02, 36.20it/s]
Loading 0:  86%|████████▌ | 435/507 [00:27<00:01, 37.93it/s]
Loading 0:  87%|████████▋ | 439/507 [00:27<00:01, 36.71it/s]
Loading 0:  88%|████████▊ | 444/507 [00:27<00:01, 39.34it/s]
Loading 0:  89%|████████▊ | 449/507 [00:27<00:01, 39.27it/s]
Loading 0:  90%|████████▉ | 454/507 [00:28<00:01, 37.99it/s]
Loading 0:  90%|█████████ | 458/507 [00:30<00:08,  5.98it/s]
Loading 0:  91%|█████████ | 461/507 [00:30<00:06,  7.23it/s]
Loading 0:  92%|█████████▏| 465/507 [00:30<00:04,  9.28it/s]
Loading 0:  93%|█████████▎| 472/507 [00:30<00:02, 14.35it/s]
Loading 0:  94%|█████████▍| 476/507 [00:30<00:01, 16.76it/s]
Loading 0:  95%|█████████▍| 481/507 [00:30<00:01, 20.91it/s]
Loading 0:  96%|█████████▌| 485/507 [00:31<00:00, 23.30it/s]
Loading 0:  97%|█████████▋| 490/507 [00:31<00:00, 27.29it/s]
Loading 0:  97%|█████████▋| 494/507 [00:31<00:00, 28.64it/s]
Loading 0:  98%|█████████▊| 499/507 [00:31<00:00, 31.88it/s]
Loading 0:  99%|█████████▉| 503/507 [00:31<00:00, 32.23it/s]
                                                            
Job chaiml-small-espresso-an-7267-v2-mkmlizer completed after 136.23s with status: succeeded
Stopping job with name chaiml-small-espresso-an-7267-v2-mkmlizer
Pipeline stage MKMLizer completed in 136.76s
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-small-espresso-an-7267-v2
Waiting for inference service chaiml-small-espresso-an-7267-v2 to be ready
Inference service chaiml-small-espresso-an-7267-v2 ready after 170.64855027198792s
Pipeline stage MKMLDeployer completed in 171.20s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.118943452835083s
Received healthy response to inference request in 2.4021120071411133s
Received healthy response to inference request in 2.4681200981140137s
Received healthy response to inference request in 2.4738521575927734s
Received healthy response to inference request in 2.555130958557129s
5 requests
0 failed requests
5th percentile: 2.4153136253356933
10th percentile: 2.4285152435302733
20th percentile: 2.4549184799194337
30th percentile: 2.4692665100097657
40th percentile: 2.4715593338012694
50th percentile: 2.4738521575927734
60th percentile: 2.5063636779785154
70th percentile: 2.538875198364258
80th percentile: 2.66789345741272
90th percentile: 2.8934184551239013
95th percentile: 3.006180953979492
99th percentile: 3.0963909530639646
mean time: 2.6036317348480225
Pipeline stage StressChecker completed in 14.19s
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 2.16s
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 1.95s
Shutdown handler de-registered
chaiml-small-espresso-an_7267_v2 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 0.11s
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-small-espresso-an-7267-v2-profiler
Waiting for inference service chaiml-small-espresso-an-7267-v2-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 3171.37s
Shutdown handler de-registered
chaiml-small-espresso-an_7267_v2 status is now inactive due to auto deactivation removed underperforming models