chaiml-small-espresso-an_7267

developer_uid: azuruce

submission_id: chaiml-small-espresso-an_7267_v1

model_name: chaiml-small-espresso-an_7267_v1

model_group: ChaiML/small_espresso_an

status: inactive

timestamp: 2024-12-06T23:48:06+00:00

num_battles: 10928

num_wins: 5633

celo_rating: 1270.79

family_friendly_score: 0.5616

family_friendly_standard_error: 0.007017199441372605

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: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.3825433336953232, 'latency_mean': 2.6140204763412473, 'latency_p50': 2.6083784103393555, 'latency_p90': 2.884892153739929}, {'batch_size': 2, 'throughput': 0.600123164134039, 'latency_mean': 3.3256231141090393, 'latency_p50': 3.3164994716644287, 'latency_p90': 3.6637664794921876}, {'batch_size': 3, 'throughput': 0.7591512289751742, 'latency_mean': 3.9369191348552706, 'latency_p50': 3.9275858402252197, 'latency_p90': 4.365804409980774}, {'batch_size': 4, 'throughput': 0.8852295197104898, 'latency_mean': 4.500001237392426, 'latency_p50': 4.506835103034973, 'latency_p90': 5.029813528060913}, {'batch_size': 5, 'throughput': 0.9783777487436338, 'latency_mean': 5.0816268658638, 'latency_p50': 5.128696322441101, 'latency_p90': 5.627916288375855}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-small-espresso-an_7267_v1

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: 0.71

us_pacific_date: 2024-12-06

win_ratio: 0.5154648609077599

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', '<|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-an-7267-v1-mkmlizer
Waiting for job on chaiml-small-espresso-an-7267-v1-mkmlizer to finish
chaiml-small-espresso-an-7267-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-small-espresso-an-7267-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-small-espresso-an-7267-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-small-espresso-an-7267-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-small-espresso-an-7267-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-small-espresso-an-7267-v1-mkmlizer: ║       /___/                                                         ║
chaiml-small-espresso-an-7267-v1-mkmlizer: ║                                                                     ║
chaiml-small-espresso-an-7267-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-small-espresso-an-7267-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-small-espresso-an-7267-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-small-espresso-an-7267-v1-mkmlizer: ║                                                                     ║
chaiml-small-espresso-an-7267-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-small-espresso-an-7267-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-small-espresso-an-7267-v1-mkmlizer: ║                                                                     ║
chaiml-small-espresso-an-7267-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-small-espresso-an-7267-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-small-espresso-an-7267-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-small-espresso-an-7267-v1-mkmlizer: ║                                                                     ║
chaiml-small-espresso-an-7267-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-small-espresso-an-7267-v1-mkmlizer: Downloaded to shared memory in 75.736s
chaiml-small-espresso-an-7267-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp441mhe9i, device:0
chaiml-small-espresso-an-7267-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-small-espresso-an-7267-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-small-espresso-an-7267-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-small-espresso-an-7267-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-small-espresso-an-7267-v1
chaiml-small-espresso-an-7267-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-small-espresso-an-7267-v1/config.json
chaiml-small-espresso-an-7267-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-small-espresso-an-7267-v1/special_tokens_map.json
chaiml-small-espresso-an-7267-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-small-espresso-an-7267-v1/tokenizer_config.json
chaiml-small-espresso-an-7267-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-small-espresso-an-7267-v1/tokenizer.json
chaiml-small-espresso-an-7267-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-small-espresso-an-7267-v1/flywheel_model.1.safetensors
chaiml-small-espresso-an-7267-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-small-espresso-an-7267-v1/flywheel_model.0.safetensors
chaiml-small-espresso-an-7267-v1-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:21, 23.79it/s]
Loading 0:   2%|▏         | 12/507 [00:00<00:12, 38.24it/s]
Loading 0:   3%|▎         | 17/507 [00:00<00:13, 37.23it/s]
Loading 0:   4%|▍         | 21/507 [00:00<00:13, 37.16it/s]
Loading 0:   5%|▍         | 25/507 [00:00<00:14, 34.32it/s]
Loading 0:   6%|▌         | 30/507 [00:00<00:12, 37.51it/s]
Loading 0:   7%|▋         | 34/507 [00:00<00:13, 35.85it/s]
Loading 0:   8%|▊         | 39/507 [00:01<00:12, 38.77it/s]
Loading 0:   8%|▊         | 43/507 [00:01<00:12, 37.23it/s]
Loading 0:   9%|▉         | 47/507 [00:01<00:12, 37.56it/s]
Loading 0:  10%|█         | 51/507 [00:01<00:12, 36.81it/s]
Loading 0:  11%|█         | 55/507 [00:01<00:18, 25.01it/s]
Loading 0:  12%|█▏        | 59/507 [00:01<00:16, 27.35it/s]
Loading 0:  12%|█▏        | 63/507 [00:01<00:14, 29.78it/s]
Loading 0:  13%|█▎        | 67/507 [00:02<00:14, 30.38it/s]
Loading 0:  14%|█▍        | 72/507 [00:02<00:12, 35.15it/s]
Loading 0:  15%|█▌        | 78/507 [00:02<00:10, 39.59it/s]
Loading 0:  16%|█▋        | 83/507 [00:02<00:11, 38.28it/s]
Loading 0:  17%|█▋        | 87/507 [00:02<00:11, 38.02it/s]
Loading 0:  18%|█▊        | 91/507 [00:02<00:11, 36.41it/s]
Loading 0:  19%|█▉        | 96/507 [00:02<00:10, 38.36it/s]
Loading 0:  20%|█▉        | 100/507 [00:02<00:11, 36.37it/s]
Loading 0:  21%|██        | 105/507 [00:02<00:10, 38.15it/s]
Loading 0:  21%|██▏       | 109/507 [00:03<00:11, 36.12it/s]
Loading 0:  22%|██▏       | 113/507 [00:03<00:14, 27.32it/s]
Loading 0:  23%|██▎       | 117/507 [00:03<00:14, 26.85it/s]
Loading 0:  24%|██▍       | 122/507 [00:03<00:13, 28.20it/s]
Loading 0:  25%|██▌       | 129/507 [00:03<00:10, 35.50it/s]
Loading 0:  26%|██▌       | 133/507 [00:03<00:10, 34.78it/s]
Loading 0:  27%|██▋       | 138/507 [00:04<00:09, 37.70it/s]
Loading 0:  28%|██▊       | 142/507 [00:04<00:10, 35.88it/s]
Loading 0:  29%|██▉       | 147/507 [00:04<00:09, 38.17it/s]
Loading 0:  30%|██▉       | 151/507 [00:04<00:09, 36.05it/s]
Loading 0:  31%|███       | 156/507 [00:04<00:08, 39.04it/s]
Loading 0:  32%|███▏      | 161/507 [00:04<00:09, 38.41it/s]
Loading 0:  33%|███▎      | 165/507 [00:04<00:08, 38.42it/s]
Loading 0:  33%|███▎      | 169/507 [00:04<00:12, 27.67it/s]
Loading 0:  34%|███▍      | 173/507 [00:05<00:11, 28.72it/s]
Loading 0:  35%|███▍      | 177/507 [00:05<00:11, 28.46it/s]
Loading 0:  36%|███▌      | 183/507 [00:05<00:09, 34.46it/s]
Loading 0:  37%|███▋      | 187/507 [00:05<00:09, 34.07it/s]
Loading 0:  38%|███▊      | 192/507 [00:05<00:08, 37.59it/s]
Loading 0:  39%|███▊      | 196/507 [00:05<00:08, 35.93it/s]
Loading 0:  40%|███▉      | 201/507 [00:05<00:07, 38.58it/s]
Loading 0:  40%|████      | 205/507 [00:05<00:08, 36.05it/s]
Loading 0:  41%|████▏     | 210/507 [00:06<00:07, 39.11it/s]
Loading 0:  42%|████▏     | 215/507 [00:06<00:07, 39.05it/s]
Loading 0:  43%|████▎     | 219/507 [00:06<00:09, 31.63it/s]
Loading 0:  44%|████▍     | 224/507 [00:06<00:10, 26.73it/s]
Loading 0:  45%|████▌     | 230/507 [00:06<00:09, 28.47it/s]
Loading 0:  47%|████▋     | 237/507 [00:06<00:07, 34.82it/s]
Loading 0:  48%|████▊     | 241/507 [00:07<00:07, 34.63it/s]
Loading 0:  49%|████▊     | 246/507 [00:07<00:07, 37.10it/s]
Loading 0:  49%|████▉     | 250/507 [00:07<00:07, 35.24it/s]
Loading 0:  50%|█████     | 255/507 [00:07<00:06, 37.11it/s]
Loading 0:  51%|█████     | 259/507 [00:07<00:07, 35.38it/s]
Loading 0:  52%|█████▏    | 264/507 [00:07<00:06, 38.01it/s]
Loading 0:  53%|█████▎    | 268/507 [00:07<00:06, 36.64it/s]
Loading 0:  54%|█████▍    | 273/507 [00:07<00:06, 38.83it/s]
Loading 0:  55%|█████▍    | 277/507 [00:08<00:06, 37.09it/s]
Loading 0:  56%|█████▌    | 283/507 [00:08<00:05, 38.75it/s]
Loading 0:  57%|█████▋    | 287/507 [00:08<00:08, 25.35it/s]
Loading 0:  58%|█████▊    | 293/507 [00:08<00:07, 28.40it/s]
Loading 0:  59%|█████▉    | 299/507 [00:23<00:07, 28.40it/s]
Loading 0:  59%|█████▉    | 300/507 [00:23<02:43,  1.27it/s]
Loading 0:  60%|█████▉    | 302/507 [00:23<02:22,  1.44it/s]
Loading 0:  61%|██████    | 307/507 [00:23<01:36,  2.08it/s]
Loading 0:  61%|██████    | 310/507 [00:23<01:16,  2.57it/s]
Loading 0:  62%|██████▏   | 314/507 [00:23<00:54,  3.52it/s]
Loading 0:  63%|██████▎   | 318/507 [00:23<00:39,  4.81it/s]
Loading 0:  64%|██████▎   | 322/507 [00:23<00:28,  6.43it/s]
Loading 0:  64%|██████▍   | 327/507 [00:23<00:19,  9.15it/s]
Loading 0:  65%|██████▌   | 331/507 [00:24<00:15, 11.46it/s]
Loading 0:  66%|██████▌   | 335/507 [00:24<00:12, 14.30it/s]
Loading 0:  67%|██████▋   | 340/507 [00:24<00:10, 16.00it/s]
Loading 0:  68%|██████▊   | 344/507 [00:24<00:08, 18.48it/s]
Loading 0:  69%|██████▊   | 348/507 [00:24<00:08, 19.77it/s]
Loading 0:  70%|██████▉   | 354/507 [00:24<00:06, 25.35it/s]
Loading 0:  71%|███████   | 358/507 [00:24<00:05, 26.47it/s]
Loading 0:  72%|███████▏  | 363/507 [00:25<00:04, 30.03it/s]
Loading 0:  72%|███████▏  | 367/507 [00:25<00:04, 30.24it/s]
Loading 0:  73%|███████▎  | 372/507 [00:25<00:04, 33.12it/s]
Loading 0:  74%|███████▍  | 376/507 [00:25<00:04, 32.30it/s]
Loading 0:  75%|███████▌  | 381/507 [00:25<00:03, 34.50it/s]
Loading 0:  76%|███████▌  | 385/507 [00:25<00:03, 34.22it/s]
Loading 0:  77%|███████▋  | 389/507 [00:25<00:03, 35.38it/s]
Loading 0:  78%|███████▊  | 393/507 [00:25<00:03, 35.04it/s]
Loading 0:  78%|███████▊  | 397/507 [00:26<00:04, 26.48it/s]
Loading 0:  79%|███████▉  | 401/507 [00:26<00:04, 26.34it/s]
Loading 0:  80%|████████  | 408/507 [00:26<00:02, 33.85it/s]
Loading 0:  81%|████████▏ | 412/507 [00:26<00:02, 33.35it/s]
Loading 0:  82%|████████▏ | 417/507 [00:26<00:02, 35.93it/s]
Loading 0:  83%|████████▎ | 421/507 [00:26<00:02, 34.88it/s]
Loading 0:  84%|████████▍ | 426/507 [00:26<00:02, 37.61it/s]
Loading 0:  85%|████████▍ | 430/507 [00:27<00:02, 35.96it/s]
Loading 0:  86%|████████▌ | 435/507 [00:27<00:01, 38.79it/s]
Loading 0:  87%|████████▋ | 439/507 [00:27<00:01, 37.26it/s]
Loading 0:  88%|████████▊ | 444/507 [00:27<00:01, 40.15it/s]
Loading 0:  89%|████████▊ | 449/507 [00:27<00:01, 39.50it/s]
Loading 0:  90%|████████▉ | 454/507 [00:27<00:01, 38.39it/s]
Loading 0:  90%|█████████ | 458/507 [00:29<00:08,  5.99it/s]
Loading 0:  91%|█████████ | 461/507 [00:30<00:06,  7.19it/s]
Loading 0:  92%|█████████▏| 465/507 [00:30<00:04,  9.23it/s]
Loading 0:  93%|█████████▎| 472/507 [00:30<00:02, 14.38it/s]
Loading 0:  94%|█████████▍| 476/507 [00:30<00:01, 16.81it/s]
Loading 0:  95%|█████████▍| 481/507 [00:30<00:01, 21.15it/s]
Loading 0:  96%|█████████▌| 485/507 [00:30<00:00, 23.53it/s]
Loading 0:  97%|█████████▋| 490/507 [00:30<00:00, 27.75it/s]
Loading 0:  97%|█████████▋| 494/507 [00:30<00:00, 28.97it/s]
Loading 0:  98%|█████████▊| 499/507 [00:30<00:00, 32.46it/s]
Loading 0:  99%|█████████▉| 503/507 [00:31<00:00, 32.76it/s]
                                                            
Job chaiml-small-espresso-an-7267-v1-mkmlizer completed after 146.33s with status: succeeded
Stopping job with name chaiml-small-espresso-an-7267-v1-mkmlizer
Pipeline stage MKMLizer completed in 146.85s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-small-espresso-an-7267-v1
Waiting for inference service chaiml-small-espresso-an-7267-v1 to be ready
Inference service chaiml-small-espresso-an-7267-v1 ready after 171.05339217185974s
Pipeline stage MKMLDeployer completed in 171.64s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.8935303688049316s
Received healthy response to inference request in 2.9924914836883545s
Received healthy response to inference request in 2.5126514434814453s
Received healthy response to inference request in 2.8858063220977783s
Received healthy response to inference request in 2.765427827835083s
5 requests
0 failed requests
5th percentile: 2.5632067203521727
10th percentile: 2.6137619972229005
20th percentile: 2.7148725509643556
30th percentile: 2.7895035266876222
40th percentile: 2.8376549243927003
50th percentile: 2.8858063220977783
60th percentile: 2.88889594078064
70th percentile: 2.891985559463501
80th percentile: 2.913322591781616
90th percentile: 2.9529070377349855
95th percentile: 2.97269926071167
99th percentile: 2.9885330390930176
mean time: 2.8099814891815185
Pipeline stage StressChecker completed in 15.32s
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 2.11s
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 1.89s
Shutdown handler de-registered
chaiml-small-espresso-an_7267_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 3278.36s
Shutdown handler de-registered
chaiml-small-espresso-an_7267_v1 status is now inactive due to auto deactivation removed underperforming models