chaiml-espresso-ant-2412_7481

developer_uid: azuruce

submission_id: chaiml-espresso-ant-2412_7481_v1

model_name: chaiml-espresso-ant-2412_7481_v1

model_group: ChaiML/espresso_ant_2412

status: inactive

timestamp: 2024-12-05T05:47:23+00:00

num_battles: 10029

num_wins: 5165

celo_rating: 1272.86

family_friendly_score: 0.5848

family_friendly_standard_error: 0.006968629133480989

submission_type: basic

model_repo: ChaiML/espresso_ant_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': 0.37615929672658427, 'latency_mean': 2.658364169597626, 'latency_p50': 2.65382182598114, 'latency_p90': 2.9617588758468627}, {'batch_size': 2, 'throughput': 0.5966064711206319, 'latency_mean': 3.3432404017448425, 'latency_p50': 3.3618075847625732, 'latency_p90': 3.667525577545166}, {'batch_size': 3, 'throughput': 0.7559294607988125, 'latency_mean': 3.9472186648845673, 'latency_p50': 3.9567956924438477, 'latency_p90': 4.349531197547912}, {'batch_size': 4, 'throughput': 0.868482825487935, 'latency_mean': 4.574369066953659, 'latency_p50': 4.605960965156555, 'latency_p90': 4.995603632926941}, {'batch_size': 5, 'throughput': 0.9597608107088152, 'latency_mean': 5.171843757629395, 'latency_p50': 5.2661741971969604, 'latency_p90': 5.691325902938843}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-espresso-ant-2412_7481_v1

is_internal_developer: True

language_model: ChaiML/espresso_ant_241204_albert_v2_sft_2epoch_128alpha

model_size: 22B

ranking_group: single

throughput_3p7s: 0.7

us_pacific_date: 2024-12-04

win_ratio: 0.515006481204507

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-2412-7481-v1-mkmlizer
Waiting for job on chaiml-espresso-ant-2412-7481-v1-mkmlizer to finish
chaiml-espresso-ant-2412-7481-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-espresso-ant-2412-7481-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-espresso-ant-2412-7481-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-espresso-ant-2412-7481-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-espresso-ant-2412-7481-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-espresso-ant-2412-7481-v1-mkmlizer: ║       /___/                                                         ║
chaiml-espresso-ant-2412-7481-v1-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-2412-7481-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-espresso-ant-2412-7481-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-espresso-ant-2412-7481-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-espresso-ant-2412-7481-v1-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-2412-7481-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-espresso-ant-2412-7481-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-espresso-ant-2412-7481-v1-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-2412-7481-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-espresso-ant-2412-7481-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-espresso-ant-2412-7481-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-espresso-ant-2412-7481-v1-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-2412-7481-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-espresso-ant-2412-7481-v1-mkmlizer: quantized model in 43.551s
chaiml-espresso-ant-2412-7481-v1-mkmlizer: Processed model ChaiML/espresso_ant_241204_albert_v2_sft_2epoch_128alpha in 114.564s
chaiml-espresso-ant-2412-7481-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-espresso-ant-2412-7481-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-espresso-ant-2412-7481-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-espresso-ant-2412-7481-v1
chaiml-espresso-ant-2412-7481-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-espresso-ant-2412-7481-v1/config.json
chaiml-espresso-ant-2412-7481-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-espresso-ant-2412-7481-v1/special_tokens_map.json
chaiml-espresso-ant-2412-7481-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-espresso-ant-2412-7481-v1/tokenizer_config.json
chaiml-espresso-ant-2412-7481-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-espresso-ant-2412-7481-v1/tokenizer.json
chaiml-espresso-ant-2412-7481-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-espresso-ant-2412-7481-v1/flywheel_model.1.safetensors
chaiml-espresso-ant-2412-7481-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-espresso-ant-2412-7481-v1/flywheel_model.0.safetensors
chaiml-espresso-ant-2412-7481-v1-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:20, 24.52it/s]
Loading 0:   2%|▏         | 12/507 [00:00<00:12, 40.75it/s]
Loading 0:   3%|▎         | 17/507 [00:00<00:12, 38.14it/s]
Loading 0:   4%|▍         | 22/507 [00:00<00:12, 39.17it/s]
Loading 0:   5%|▌         | 27/507 [00:00<00:11, 40.05it/s]
Loading 0:   6%|▋         | 32/507 [00:00<00:13, 34.17it/s]
Loading 0:   8%|▊         | 39/507 [00:01<00:11, 41.16it/s]
Loading 0:   9%|▊         | 44/507 [00:01<00:11, 39.66it/s]
Loading 0:  10%|▉         | 49/507 [00:01<00:13, 33.17it/s]
Loading 0:  10%|█         | 53/507 [00:01<00:17, 25.48it/s]
Loading 0:  11%|█         | 56/507 [00:01<00:19, 23.20it/s]
Loading 0:  12%|█▏        | 63/507 [00:01<00:14, 29.99it/s]
Loading 0:  13%|█▎        | 67/507 [00:02<00:14, 30.59it/s]
Loading 0:  14%|█▍        | 73/507 [00:02<00:13, 32.78it/s]
Loading 0:  16%|█▌        | 80/507 [00:02<00:12, 33.83it/s]
Loading 0:  17%|█▋        | 87/507 [00:02<00:10, 38.37it/s]
Loading 0:  18%|█▊        | 91/507 [00:02<00:11, 36.31it/s]
Loading 0:  19%|█▉        | 96/507 [00:02<00:11, 37.08it/s]
Loading 0:  20%|█▉        | 100/507 [00:02<00:11, 35.47it/s]
Loading 0:  21%|██        | 105/507 [00:03<00:10, 38.17it/s]
Loading 0:  21%|██▏       | 109/507 [00:03<00:10, 36.70it/s]
Loading 0:  22%|██▏       | 113/507 [00:03<00:14, 26.70it/s]
Loading 0:  23%|██▎       | 117/507 [00:03<00:15, 25.87it/s]
Loading 0:  24%|██▍       | 122/507 [00:03<00:14, 26.39it/s]
Loading 0:  25%|██▌       | 129/507 [00:03<00:11, 32.93it/s]
Loading 0:  26%|██▌       | 133/507 [00:04<00:11, 32.36it/s]
Loading 0:  27%|██▋       | 138/507 [00:04<00:10, 34.99it/s]
Loading 0:  28%|██▊       | 142/507 [00:04<00:10, 33.40it/s]
Loading 0:  29%|██▉       | 147/507 [00:04<00:09, 36.40it/s]
Loading 0:  30%|██▉       | 151/507 [00:04<00:10, 35.28it/s]
Loading 0:  31%|███       | 156/507 [00:04<00:09, 37.79it/s]
Loading 0:  32%|███▏      | 160/507 [00:04<00:09, 36.12it/s]
Loading 0:  32%|███▏      | 164/507 [00:04<00:09, 36.61it/s]
Loading 0:  33%|███▎      | 169/507 [00:05<00:12, 26.54it/s]
Loading 0:  34%|███▍      | 173/507 [00:05<00:12, 27.65it/s]
Loading 0:  35%|███▍      | 177/507 [00:05<00:12, 26.92it/s]
Loading 0:  36%|███▌      | 183/507 [00:05<00:09, 32.74it/s]
Loading 0:  37%|███▋      | 187/507 [00:05<00:09, 32.42it/s]
Loading 0:  38%|███▊      | 192/507 [00:05<00:08, 35.06it/s]
Loading 0:  39%|███▊      | 196/507 [00:05<00:09, 33.37it/s]
Loading 0:  40%|███▉      | 201/507 [00:06<00:08, 35.29it/s]
Loading 0:  40%|████      | 205/507 [00:06<00:08, 34.87it/s]
Loading 0:  41%|████▏     | 210/507 [00:06<00:08, 36.24it/s]
Loading 0:  42%|████▏     | 214/507 [00:06<00:08, 36.24it/s]
Loading 0:  43%|████▎     | 219/507 [00:06<00:08, 33.00it/s]
Loading 0:  44%|████▍     | 224/507 [00:06<00:10, 27.31it/s]
Loading 0:  45%|████▌     | 230/507 [00:07<00:09, 28.85it/s]
Loading 0:  47%|████▋     | 237/507 [00:07<00:07, 35.45it/s]
Loading 0:  48%|████▊     | 241/507 [00:07<00:07, 34.90it/s]
Loading 0:  49%|████▊     | 246/507 [00:07<00:07, 36.82it/s]
Loading 0:  49%|████▉     | 250/507 [00:07<00:07, 35.75it/s]
Loading 0:  50%|█████     | 255/507 [00:07<00:06, 38.05it/s]
Loading 0:  51%|█████     | 259/507 [00:07<00:06, 36.93it/s]
Loading 0:  52%|█████▏    | 264/507 [00:07<00:06, 39.01it/s]
Loading 0:  53%|█████▎    | 268/507 [00:07<00:06, 37.11it/s]
Loading 0:  54%|█████▍    | 273/507 [00:08<00:06, 38.73it/s]
Loading 0:  55%|█████▍    | 277/507 [00:08<00:06, 36.53it/s]
Loading 0:  56%|█████▌    | 283/507 [00:08<00:05, 38.52it/s]
Loading 0:  57%|█████▋    | 287/507 [00:08<00:09, 24.32it/s]
Loading 0:  58%|█████▊    | 293/507 [00:08<00:07, 27.66it/s]
Loading 0:  59%|█████▉    | 299/507 [00:23<00:07, 27.66it/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<01:37,  2.06it/s]
Loading 0:  61%|██████    | 310/507 [00:23<01:16,  2.56it/s]
Loading 0:  62%|██████▏   | 315/507 [00:23<00:51,  3.76it/s]
Loading 0:  63%|██████▎   | 319/507 [00:24<00:37,  5.02it/s]
Loading 0:  64%|██████▍   | 324/507 [00:24<00:25,  7.16it/s]
Loading 0:  65%|██████▍   | 328/507 [00:24<00:19,  9.22it/s]
Loading 0:  66%|██████▌   | 333/507 [00:24<00:13, 12.52it/s]
Loading 0:  67%|██████▋   | 338/507 [00:24<00:10, 16.44it/s]
Loading 0:  68%|██████▊   | 343/507 [00:24<00:10, 15.89it/s]
Loading 0:  68%|██████▊   | 347/507 [00:24<00:08, 17.93it/s]
Loading 0:  70%|██████▉   | 354/507 [00:25<00:06, 25.05it/s]
Loading 0:  71%|███████   | 359/507 [00:25<00:05, 27.24it/s]
Loading 0:  72%|███████▏  | 364/507 [00:25<00:04, 30.19it/s]
Loading 0:  73%|███████▎  | 369/507 [00:25<00:04, 33.55it/s]
Loading 0:  74%|███████▍  | 374/507 [00:25<00:04, 30.50it/s]
Loading 0:  75%|███████▌  | 381/507 [00:25<00:03, 38.17it/s]
Loading 0:  76%|███████▌  | 386/507 [00:25<00:03, 38.96it/s]
Loading 0:  77%|███████▋  | 391/507 [00:26<00:03, 35.55it/s]
Loading 0:  78%|███████▊  | 395/507 [00:26<00:04, 27.93it/s]
Loading 0:  79%|███████▉  | 401/507 [00:26<00:03, 29.55it/s]
Loading 0:  80%|████████  | 408/507 [00:26<00:02, 36.07it/s]
Loading 0:  81%|████████▏ | 413/507 [00:26<00:02, 36.69it/s]
Loading 0:  82%|████████▏ | 418/507 [00:26<00:02, 37.89it/s]
Loading 0:  83%|████████▎ | 423/507 [00:26<00:02, 39.94it/s]
Loading 0:  84%|████████▍ | 428/507 [00:27<00:02, 32.84it/s]
Loading 0:  86%|████████▌ | 435/507 [00:27<00:01, 40.02it/s]
Loading 0:  87%|████████▋ | 440/507 [00:27<00:01, 40.68it/s]
Loading 0:  88%|████████▊ | 445/507 [00:27<00:01, 41.27it/s]
Loading 0:  89%|████████▉ | 450/507 [00:27<00:01, 43.38it/s]
Loading 0:  90%|████████▉ | 455/507 [00:29<00:07,  6.82it/s]
Loading 0:  91%|█████████ | 459/507 [00:29<00:05,  8.33it/s]
Loading 0:  92%|█████████▏| 465/507 [00:30<00:03, 11.46it/s]
Loading 0:  93%|█████████▎| 472/507 [00:30<00:02, 16.30it/s]
Loading 0:  94%|█████████▍| 477/507 [00:30<00:01, 19.30it/s]
Loading 0:  95%|█████████▌| 482/507 [00:30<00:01, 22.75it/s]
Loading 0:  96%|█████████▌| 487/507 [00:30<00:00, 26.61it/s]
Loading 0:  97%|█████████▋| 492/507 [00:30<00:00, 26.56it/s]
Loading 0:  98%|█████████▊| 499/507 [00:30<00:00, 33.10it/s]
Loading 0:  99%|█████████▉| 504/507 [00:31<00:00, 34.51it/s]
                                                            
Job chaiml-espresso-ant-2412-7481-v1-mkmlizer completed after 142.86s with status: succeeded
Stopping job with name chaiml-espresso-ant-2412-7481-v1-mkmlizer
Pipeline stage MKMLizer completed in 144.60s
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-2412-7481-v1
Waiting for inference service chaiml-espresso-ant-2412-7481-v1 to be ready
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-2412-7481-v1 ready after 174.05196356773376s
Pipeline stage MKMLDeployer completed in 175.55s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.024193525314331s
Received healthy response to inference request in 2.7891757488250732s
Received healthy response to inference request in 2.4883434772491455s
Received healthy response to inference request in 2.6582961082458496s
Received healthy response to inference request in 2.33566951751709s
5 requests
0 failed requests
5th percentile: 2.366204309463501
10th percentile: 2.396739101409912
20th percentile: 2.4578086853027346
30th percentile: 2.5223340034484862
40th percentile: 2.590315055847168
50th percentile: 2.6582961082458496
60th percentile: 2.710647964477539
70th percentile: 2.7629998207092283
80th percentile: 2.8361793041229246
90th percentile: 2.930186414718628
95th percentile: 2.9771899700164797
99th percentile: 3.014792814254761
mean time: 2.659135675430298
Pipeline stage StressChecker completed in 14.71s
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 2.17s
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 2.08s
Shutdown handler de-registered
chaiml-espresso-ant-2412_7481_v1 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 3207.00s
Shutdown handler de-registered
chaiml-espresso-ant-2412_7481_v1 status is now inactive due to auto deactivation removed underperforming models