chaiml-small-espresso-a_6112

developer_uid: azuruce

submission_id: chaiml-small-espresso-a_6112_v10

model_name: chaiml-small-espresso-a_6112_v10

model_group: ChaiML/small_espresso_an

status: inactive

timestamp: 2024-12-06T18:32:10+00:00

num_battles: 9578

num_wins: 4923

celo_rating: 1273.5

family_friendly_score: 0.5808

family_friendly_standard_error: 0.006978128115762852

submission_type: basic

model_repo: ChaiML/small_espresso_ant_llama_story_241205_albert_v1_sft-3e128a

model_architecture: MistralForCausalLM

model_num_parameters: 22247282688.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.375434570493925, 'latency_mean': 2.66349871635437, 'latency_p50': 2.663572311401367, 'latency_p90': 2.941915202140808}, {'batch_size': 2, 'throughput': 0.5933193863920042, 'latency_mean': 3.3605534172058107, 'latency_p50': 3.349422574043274, 'latency_p90': 3.6909106969833374}, {'batch_size': 3, 'throughput': 0.7579754686279659, 'latency_mean': 3.940953868627548, 'latency_p50': 3.9039368629455566, 'latency_p90': 4.421275901794433}, {'batch_size': 4, 'throughput': 0.8797158685100938, 'latency_mean': 4.531868150234223, 'latency_p50': 4.550925612449646, 'latency_p90': 5.092758893966675}, {'batch_size': 5, 'throughput': 0.9617425791279728, 'latency_mean': 5.17144393324852, 'latency_p50': 5.199358105659485, 'latency_p90': 5.805011868476868}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-small-espresso-a_6112_v10

is_internal_developer: True

language_model: ChaiML/small_espresso_ant_llama_story_241205_albert_v1_sft-3e128a

model_size: 22B

ranking_group: single

throughput_3p7s: 0.7

us_pacific_date: 2024-12-06

win_ratio: 0.5139903946544163

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 100, '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-small-espresso-a-6112-v10-mkmlizer
Waiting for job on chaiml-small-espresso-a-6112-v10-mkmlizer to finish
chaiml-small-espresso-a-6112-v10-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-small-espresso-a-6112-v10-mkmlizer: ║     _____            __           __                                ║
chaiml-small-espresso-a-6112-v10-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-small-espresso-a-6112-v10-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-small-espresso-a-6112-v10-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-small-espresso-a-6112-v10-mkmlizer: ║       /___/                                                         ║
chaiml-small-espresso-a-6112-v10-mkmlizer: ║                                                                     ║
chaiml-small-espresso-a-6112-v10-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-small-espresso-a-6112-v10-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-small-espresso-a-6112-v10-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-small-espresso-a-6112-v10-mkmlizer: ║                                                                     ║
chaiml-small-espresso-a-6112-v10-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-small-espresso-a-6112-v10-mkmlizer: ║  belonging to:                                                      ║
chaiml-small-espresso-a-6112-v10-mkmlizer: ║                                                                     ║
chaiml-small-espresso-a-6112-v10-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-small-espresso-a-6112-v10-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-small-espresso-a-6112-v10-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-small-espresso-a-6112-v10-mkmlizer: ║                                                                     ║
chaiml-small-espresso-a-6112-v10-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-small-espresso-a-6112-v10-mkmlizer: Downloaded to shared memory in 52.422s
chaiml-small-espresso-a-6112-v10-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpm3vgyg1m, device:0
chaiml-small-espresso-a-6112-v10-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-small-espresso-a-6112-v10-mkmlizer: quantized model in 43.287s
chaiml-small-espresso-a-6112-v10-mkmlizer: Processed model ChaiML/small_espresso_ant_llama_story_241205_albert_v1_sft-3e128a in 95.709s
chaiml-small-espresso-a-6112-v10-mkmlizer: creating bucket guanaco-mkml-models
chaiml-small-espresso-a-6112-v10-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-small-espresso-a-6112-v10/config.json
chaiml-small-espresso-a-6112-v10-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-small-espresso-a-6112-v10/special_tokens_map.json
chaiml-small-espresso-a-6112-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-small-espresso-a-6112-v10/tokenizer_config.json
chaiml-small-espresso-a-6112-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-small-espresso-a-6112-v10/tokenizer.json
chaiml-small-espresso-a-6112-v10-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-small-espresso-a-6112-v10/flywheel_model.1.safetensors
chaiml-small-espresso-a-6112-v10-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-small-espresso-a-6112-v10/flywheel_model.0.safetensors
chaiml-small-espresso-a-6112-v10-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:20, 24.28it/s]
Loading 0:   2%|▏         | 12/507 [00:00<00:12, 40.30it/s]
Loading 0:   3%|▎         | 17/507 [00:00<00:13, 37.01it/s]
Loading 0:   4%|▍         | 22/507 [00:00<00:12, 38.07it/s]
Loading 0:   5%|▌         | 26/507 [00:00<00:12, 38.05it/s]
Loading 0:   6%|▌         | 31/507 [00:00<00:12, 39.07it/s]
Loading 0:   7%|▋         | 35/507 [00:00<00:12, 38.50it/s]
Loading 0:   8%|▊         | 40/507 [00:01<00:11, 39.42it/s]
Loading 0:   9%|▊         | 44/507 [00:01<00:11, 39.13it/s]
Loading 0:   9%|▉         | 48/507 [00:01<00:14, 31.22it/s]
Loading 0:  10%|█         | 53/507 [00:01<00:17, 25.63it/s]
Loading 0:  11%|█         | 56/507 [00:01<00:18, 23.81it/s]
Loading 0:  12%|█▏        | 63/507 [00:01<00:14, 31.63it/s]
Loading 0:  13%|█▎        | 67/507 [00:02<00:13, 32.14it/s]
Loading 0:  14%|█▍        | 73/507 [00:02<00:12, 34.88it/s]
Loading 0:  16%|█▌        | 80/507 [00:02<00:11, 36.02it/s]
Loading 0:  17%|█▋        | 87/507 [00:02<00:10, 40.27it/s]
Loading 0:  18%|█▊        | 92/507 [00:02<00:10, 38.81it/s]
Loading 0:  19%|█▉        | 96/507 [00:02<00:10, 38.28it/s]
Loading 0:  20%|█▉        | 100/507 [00:02<00:11, 36.03it/s]
Loading 0:  21%|██        | 105/507 [00:02<00:10, 37.76it/s]
Loading 0:  21%|██▏       | 109/507 [00:03<00:10, 36.81it/s]
Loading 0:  22%|██▏       | 113/507 [00:03<00:14, 27.99it/s]
Loading 0:  23%|██▎       | 117/507 [00:03<00:14, 27.20it/s]
Loading 0:  24%|██▍       | 122/507 [00:03<00:13, 28.02it/s]
Loading 0:  25%|██▌       | 129/507 [00:03<00:10, 34.92it/s]
Loading 0:  26%|██▌       | 133/507 [00:03<00:11, 33.99it/s]
Loading 0:  27%|██▋       | 138/507 [00:04<00:10, 36.74it/s]
Loading 0:  28%|██▊       | 142/507 [00:04<00:10, 35.22it/s]
Loading 0:  29%|██▉       | 147/507 [00:04<00:09, 38.15it/s]
Loading 0:  30%|██▉       | 151/507 [00:04<00:10, 35.48it/s]
Loading 0:  31%|███       | 156/507 [00:04<00:09, 38.10it/s]
Loading 0:  32%|███▏      | 160/507 [00:04<00:09, 36.83it/s]
Loading 0:  32%|███▏      | 164/507 [00:04<00:09, 37.32it/s]
Loading 0:  33%|███▎      | 169/507 [00:04<00:11, 28.70it/s]
Loading 0:  34%|███▍      | 173/507 [00:05<00:11, 28.70it/s]
Loading 0:  35%|███▍      | 177/507 [00:05<00:11, 28.10it/s]
Loading 0:  36%|███▌      | 183/507 [00:05<00:09, 33.54it/s]
Loading 0:  37%|███▋      | 187/507 [00:05<00:09, 32.88it/s]
Loading 0:  38%|███▊      | 192/507 [00:05<00:08, 35.81it/s]
Loading 0:  39%|███▊      | 196/507 [00:05<00:09, 34.54it/s]
Loading 0:  40%|███▉      | 201/507 [00:05<00:08, 37.30it/s]
Loading 0:  40%|████      | 205/507 [00:05<00:08, 36.01it/s]
Loading 0:  41%|████▏     | 210/507 [00:06<00:07, 38.07it/s]
Loading 0:  42%|████▏     | 214/507 [00:06<00:08, 36.54it/s]
Loading 0:  43%|████▎     | 218/507 [00:06<00:07, 36.17it/s]
Loading 0:  44%|████▍     | 222/507 [00:06<00:08, 34.59it/s]
Loading 0:  45%|████▍     | 226/507 [00:06<00:10, 25.62it/s]
Loading 0:  45%|████▌     | 230/507 [00:06<00:10, 25.52it/s]
Loading 0:  47%|████▋     | 237/507 [00:07<00:08, 32.87it/s]
Loading 0:  48%|████▊     | 241/507 [00:07<00:08, 32.37it/s]
Loading 0:  49%|████▊     | 246/507 [00:07<00:07, 34.73it/s]
Loading 0:  49%|████▉     | 250/507 [00:07<00:07, 33.66it/s]
Loading 0:  50%|█████     | 255/507 [00:07<00:07, 35.84it/s]
Loading 0:  51%|█████     | 259/507 [00:07<00:07, 34.28it/s]
Loading 0:  52%|█████▏    | 264/507 [00:07<00:06, 36.63it/s]
Loading 0:  53%|█████▎    | 268/507 [00:07<00:06, 34.65it/s]
Loading 0:  54%|█████▍    | 273/507 [00:08<00:06, 37.05it/s]
Loading 0:  55%|█████▍    | 277/507 [00:08<00:06, 35.85it/s]
Loading 0:  56%|█████▌    | 283/507 [00:08<00:05, 37.96it/s]
Loading 0:  57%|█████▋    | 287/507 [00:08<00:08, 24.95it/s]
Loading 0:  58%|█████▊    | 293/507 [00:08<00:07, 27.81it/s]
Loading 0:  59%|█████▉    | 299/507 [00:23<00:07, 27.81it/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 [00:23<00:55,  3.48it/s]
Loading 0:  63%|██████▎   | 319/507 [00:24<00:37,  5.06it/s]
Loading 0:  64%|██████▎   | 323/507 [00:24<00:27,  6.70it/s]
Loading 0:  65%|██████▍   | 328/507 [00:24<00:19,  9.30it/s]
Loading 0:  65%|██████▌   | 332/507 [00:24<00:14, 11.72it/s]
Loading 0:  66%|██████▋   | 337/507 [00:24<00:10, 15.54it/s]
Loading 0:  67%|██████▋   | 341/507 [00:24<00:10, 15.46it/s]
Loading 0:  68%|██████▊   | 345/507 [00:24<00:09, 17.87it/s]
Loading 0:  69%|██████▉   | 349/507 [00:25<00:07, 20.15it/s]
Loading 0:  70%|██████▉   | 354/507 [00:25<00:06, 24.54it/s]
Loading 0:  71%|███████   | 358/507 [00:25<00:05, 26.44it/s]
Loading 0:  72%|███████▏  | 363/507 [00:25<00:04, 30.15it/s]
Loading 0:  72%|███████▏  | 367/507 [00:25<00:04, 30.66it/s]
Loading 0:  73%|███████▎  | 372/507 [00:25<00:03, 34.64it/s]
Loading 0:  74%|███████▍  | 376/507 [00:25<00:03, 34.41it/s]
Loading 0:  75%|███████▌  | 381/507 [00:25<00:03, 37.82it/s]
Loading 0:  76%|███████▌  | 386/507 [00:25<00:03, 38.34it/s]
Loading 0:  77%|███████▋  | 391/507 [00:26<00:03, 33.99it/s]
Loading 0:  78%|███████▊  | 395/507 [00:26<00:04, 26.57it/s]
Loading 0:  79%|███████▉  | 401/507 [00:26<00:03, 28.18it/s]
Loading 0:  80%|████████  | 408/507 [00:26<00:02, 34.65it/s]
Loading 0:  81%|████████▏ | 412/507 [00:26<00:02, 34.23it/s]
Loading 0:  82%|████████▏ | 417/507 [00:26<00:02, 36.82it/s]
Loading 0:  83%|████████▎ | 421/507 [00:27<00:02, 35.46it/s]
Loading 0:  84%|████████▍ | 426/507 [00:27<00:02, 38.13it/s]
Loading 0:  85%|████████▍ | 430/507 [00:27<00:02, 36.61it/s]
Loading 0:  86%|████████▌ | 435/507 [00:27<00:01, 39.41it/s]
Loading 0:  87%|████████▋ | 440/507 [00:27<00:01, 39.05it/s]
Loading 0:  88%|████████▊ | 444/507 [00:27<00:01, 38.62it/s]
Loading 0:  88%|████████▊ | 448/507 [00:27<00:01, 37.53it/s]
Loading 0:  90%|████████▉ | 454/507 [00:27<00:01, 39.59it/s]
Loading 0:  90%|█████████ | 458/507 [00:30<00:07,  6.13it/s]
Loading 0:  91%|█████████ | 461/507 [00:30<00:06,  7.36it/s]
Loading 0:  92%|█████████▏| 465/507 [00:30<00:04,  9.36it/s]
Loading 0:  93%|█████████▎| 472/507 [00:30<00:02, 14.42it/s]
Loading 0:  94%|█████████▍| 476/507 [00:30<00:01, 16.76it/s]
Loading 0:  95%|█████████▍| 481/507 [00:30<00:01, 20.80it/s]
Loading 0:  96%|█████████▌| 485/507 [00:30<00:00, 22.92it/s]
Loading 0:  97%|█████████▋| 490/507 [00:30<00:00, 26.78it/s]
Loading 0:  97%|█████████▋| 494/507 [00:31<00:00, 27.88it/s]
Loading 0:  98%|█████████▊| 499/507 [00:31<00:00, 31.46it/s]
Loading 0:  99%|█████████▉| 503/507 [00:31<00:00, 31.68it/s]
                                                            
Job chaiml-small-espresso-a-6112-v10-mkmlizer completed after 127.59s with status: succeeded
Stopping job with name chaiml-small-espresso-a-6112-v10-mkmlizer
Pipeline stage MKMLizer completed in 128.06s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-small-espresso-a-6112-v10
Waiting for inference service chaiml-small-espresso-a-6112-v10 to be ready
Inference service chaiml-small-espresso-a-6112-v10 ready after 170.66256165504456s
Pipeline stage MKMLDeployer completed in 171.11s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.8656997680664062s
Received healthy response to inference request in 2.4373421669006348s
Received healthy response to inference request in 2.439357280731201s
Received healthy response to inference request in 2.8624305725097656s
Received healthy response to inference request in 2.4335646629333496s
5 requests
0 failed requests
5th percentile: 2.434320163726807
10th percentile: 2.4350756645202636
20th percentile: 2.4365866661071776
30th percentile: 2.437745189666748
40th percentile: 2.4385512351989744
50th percentile: 2.439357280731201
60th percentile: 2.6085865974426268
70th percentile: 2.777815914154053
80th percentile: 2.863084411621094
90th percentile: 2.86439208984375
95th percentile: 2.865045928955078
99th percentile: 2.8655690002441405
mean time: 2.6076788902282715
Pipeline stage StressChecker completed in 14.43s
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 2.70s
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 2.05s
Shutdown handler de-registered
chaiml-small-espresso-a_6112_v10 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 3285.83s
Shutdown handler de-registered
chaiml-small-espresso-a_6112_v10 status is now inactive due to auto deactivation removed underperforming models