chaiml-small-espresso-an_6112

developer_uid: azuruce

submission_id: chaiml-small-espresso-an_6112_v5

model_name: chaiml-small-espresso-an_6112_v5

model_group: ChaiML/small_espresso_an

status: inactive

timestamp: 2024-12-06T16:03:04+00:00

num_battles: 11994

num_wins: 6313

celo_rating: 1279.08

family_friendly_score: 0.579

family_friendly_standard_error: 0.006982248921371967

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': 0.3768615060403895, 'latency_mean': 2.6534180390834807, 'latency_p50': 2.6603835821151733, 'latency_p90': 2.8909934997558593}, {'batch_size': 2, 'throughput': 0.5959771903407608, 'latency_mean': 3.3554314613342284, 'latency_p50': 3.334148645401001, 'latency_p90': 3.7036378383636475}, {'batch_size': 3, 'throughput': 0.7493843230666114, 'latency_mean': 3.9917205488681793, 'latency_p50': 3.976775646209717, 'latency_p90': 4.387279534339905}, {'batch_size': 4, 'throughput': 0.8709469914430708, 'latency_mean': 4.5828464448452, 'latency_p50': 4.573874831199646, 'latency_p90': 5.066918206214905}, {'batch_size': 5, 'throughput': 0.956691654976631, 'latency_mean': 5.204784922599792, 'latency_p50': 5.1917994022369385, 'latency_p90': 5.813526892662048}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-small-espresso-an_6112_v5

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: 0.69

us_pacific_date: 2024-12-06

win_ratio: 0.5263465065866266

generation_params: {'temperature': 1.25, 'top_p': 0.99, 'min_p': 0.01, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', '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-6112-v5-mkmlizer
Waiting for job on chaiml-small-espresso-an-6112-v5-mkmlizer to finish
chaiml-small-espresso-an-6112-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-small-espresso-an-6112-v5-mkmlizer: ║     _____            __           __                                ║
chaiml-small-espresso-an-6112-v5-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-small-espresso-an-6112-v5-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-small-espresso-an-6112-v5-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-small-espresso-an-6112-v5-mkmlizer: ║       /___/                                                         ║
chaiml-small-espresso-an-6112-v5-mkmlizer: ║                                                                     ║
chaiml-small-espresso-an-6112-v5-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-small-espresso-an-6112-v5-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-small-espresso-an-6112-v5-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-small-espresso-an-6112-v5-mkmlizer: ║                                                                     ║
chaiml-small-espresso-an-6112-v5-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-small-espresso-an-6112-v5-mkmlizer: ║  belonging to:                                                      ║
chaiml-small-espresso-an-6112-v5-mkmlizer: ║                                                                     ║
chaiml-small-espresso-an-6112-v5-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-small-espresso-an-6112-v5-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-small-espresso-an-6112-v5-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-small-espresso-an-6112-v5-mkmlizer: ║                                                                     ║
chaiml-small-espresso-an-6112-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-small-espresso-an-6112-v5-mkmlizer: Downloaded to shared memory in 48.036s
chaiml-small-espresso-an-6112-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpp0myhqh6, device:0
chaiml-small-espresso-an-6112-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-small-espresso-an-6112-v5-mkmlizer: quantized model in 42.969s
chaiml-small-espresso-an-6112-v5-mkmlizer: Processed model ChaiML/small_espresso_ant_llama_story_241205_albert_v1_sft-3e128a in 91.005s
chaiml-small-espresso-an-6112-v5-mkmlizer: creating bucket guanaco-mkml-models
chaiml-small-espresso-an-6112-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-small-espresso-an-6112-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-small-espresso-an-6112-v5
chaiml-small-espresso-an-6112-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-small-espresso-an-6112-v5/config.json
chaiml-small-espresso-an-6112-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-small-espresso-an-6112-v5/special_tokens_map.json
chaiml-small-espresso-an-6112-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-small-espresso-an-6112-v5/tokenizer_config.json
chaiml-small-espresso-an-6112-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-small-espresso-an-6112-v5/tokenizer.json
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-small-espresso-an-6112-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-small-espresso-an-6112-v5/flywheel_model.1.safetensors
chaiml-small-espresso-an-6112-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-small-espresso-an-6112-v5/flywheel_model.0.safetensors
chaiml-small-espresso-an-6112-v5-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:20, 24.30it/s]
Loading 0:   2%|▏         | 12/507 [00:00<00:12, 39.20it/s]
Loading 0:   3%|▎         | 17/507 [00:00<00:12, 38.54it/s]
Loading 0:   4%|▍         | 22/507 [00:00<00:12, 40.20it/s]
Loading 0:   5%|▌         | 27/507 [00:00<00:11, 42.10it/s]
Loading 0:   6%|▋         | 32/507 [00:00<00:13, 35.28it/s]
Loading 0:   8%|▊         | 39/507 [00:00<00:10, 43.01it/s]
Loading 0:   9%|▊         | 44/507 [00:01<00:10, 42.82it/s]
Loading 0:  10%|▉         | 49/507 [00:01<00:12, 37.77it/s]
Loading 0:  11%|█         | 54/507 [00:01<00:15, 28.44it/s]
Loading 0:  11%|█▏        | 58/507 [00:01<00:15, 29.06it/s]
Loading 0:  12%|█▏        | 63/507 [00:01<00:13, 32.27it/s]
Loading 0:  13%|█▎        | 67/507 [00:01<00:13, 32.49it/s]
Loading 0:  14%|█▍        | 73/507 [00:02<00:12, 35.27it/s]
Loading 0:  16%|█▌        | 80/507 [00:02<00:11, 37.14it/s]
Loading 0:  17%|█▋        | 87/507 [00:02<00:09, 42.40it/s]
Loading 0:  18%|█▊        | 92/507 [00:02<00:10, 40.22it/s]
Loading 0:  19%|█▉        | 97/507 [00:02<00:10, 39.69it/s]
Loading 0:  20%|██        | 102/507 [00:02<00:09, 40.87it/s]
Loading 0:  21%|██        | 107/507 [00:02<00:11, 33.92it/s]
Loading 0:  22%|██▏       | 113/507 [00:03<00:13, 28.83it/s]
Loading 0:  23%|██▎       | 117/507 [00:03<00:14, 27.60it/s]
Loading 0:  24%|██▍       | 122/507 [00:03<00:13, 28.54it/s]
Loading 0:  25%|██▌       | 129/507 [00:03<00:10, 35.41it/s]
Loading 0:  26%|██▌       | 133/507 [00:03<00:10, 35.23it/s]
Loading 0:  27%|██▋       | 138/507 [00:03<00:09, 38.16it/s]
Loading 0:  28%|██▊       | 143/507 [00:04<00:09, 38.34it/s]
Loading 0:  29%|██▉       | 148/507 [00:04<00:09, 39.37it/s]
Loading 0:  30%|███       | 153/507 [00:04<00:08, 40.87it/s]
Loading 0:  31%|███       | 158/507 [00:04<00:09, 35.41it/s]
Loading 0:  32%|███▏      | 164/507 [00:04<00:08, 40.96it/s]
Loading 0:  33%|███▎      | 169/507 [00:04<00:10, 31.39it/s]
Loading 0:  34%|███▍      | 173/507 [00:04<00:10, 31.63it/s]
Loading 0:  35%|███▍      | 177/507 [00:05<00:10, 30.66it/s]
Loading 0:  36%|███▌      | 183/507 [00:05<00:08, 36.46it/s]
Loading 0:  37%|███▋      | 187/507 [00:05<00:08, 36.11it/s]
Loading 0:  38%|███▊      | 192/507 [00:05<00:07, 39.43it/s]
Loading 0:  39%|███▉      | 197/507 [00:05<00:08, 37.30it/s]
Loading 0:  40%|███▉      | 202/507 [00:05<00:07, 39.02it/s]
Loading 0:  41%|████      | 208/507 [00:05<00:07, 38.20it/s]
Loading 0:  42%|████▏     | 212/507 [00:05<00:08, 34.84it/s]
Loading 0:  43%|████▎     | 218/507 [00:06<00:07, 40.54it/s]
Loading 0:  44%|████▍     | 223/507 [00:06<00:07, 37.70it/s]
Loading 0:  45%|████▍     | 227/507 [00:06<00:08, 31.17it/s]
Loading 0:  46%|████▌     | 231/507 [00:06<00:09, 30.00it/s]
Loading 0:  47%|████▋     | 237/507 [00:06<00:07, 34.35it/s]
Loading 0:  48%|████▊     | 241/507 [00:06<00:07, 34.42it/s]
Loading 0:  49%|████▊     | 246/507 [00:06<00:07, 35.36it/s]
Loading 0:  49%|████▉     | 250/507 [00:07<00:07, 32.97it/s]
Loading 0:  50%|█████     | 255/507 [00:07<00:07, 34.36it/s]
Loading 0:  51%|█████     | 259/507 [00:07<00:07, 33.35it/s]
Loading 0:  52%|█████▏    | 264/507 [00:07<00:06, 35.73it/s]
Loading 0:  53%|█████▎    | 268/507 [00:07<00:06, 34.91it/s]
Loading 0:  54%|█████▍    | 273/507 [00:07<00:06, 37.50it/s]
Loading 0:  55%|█████▍    | 277/507 [00:07<00:06, 34.91it/s]
Loading 0:  56%|█████▌    | 282/507 [00:07<00:05, 38.06it/s]
Loading 0:  56%|█████▋    | 286/507 [00:08<00:08, 25.50it/s]
Loading 0:  57%|█████▋    | 290/507 [00:08<00:07, 27.45it/s]
Loading 0:  58%|█████▊    | 294/507 [00:08<00:07, 27.15it/s]
Loading 0:  59%|█████▉    | 299/507 [00:23<00:07, 27.15it/s]
Loading 0:  59%|█████▉    | 300/507 [00:23<03:16,  1.05it/s]
Loading 0:  60%|█████▉    | 302/507 [00:23<02:47,  1.22it/s]
Loading 0:  61%|██████    | 307/507 [00:23<01:47,  1.85it/s]
Loading 0:  61%|██████    | 310/507 [00:23<01:23,  2.35it/s]
Loading 0:  62%|██████▏   | 313/507 [00:23<01:03,  3.05it/s]
Loading 0:  63%|██████▎   | 318/507 [00:23<00:40,  4.67it/s]
Loading 0:  64%|██████▎   | 322/507 [00:23<00:29,  6.29it/s]
Loading 0:  64%|██████▍   | 327/507 [00:24<00:20,  9.00it/s]
Loading 0:  65%|██████▌   | 331/507 [00:24<00:15, 11.31it/s]
Loading 0:  66%|██████▌   | 335/507 [00:24<00:12, 14.14it/s]
Loading 0:  67%|██████▋   | 340/507 [00:24<00:10, 15.52it/s]
Loading 0:  68%|██████▊   | 344/507 [00:24<00:08, 18.12it/s]
Loading 0:  69%|██████▊   | 348/507 [00:24<00:08, 19.83it/s]
Loading 0:  70%|██████▉   | 354/507 [00:24<00:05, 25.87it/s]
Loading 0:  71%|███████   | 358/507 [00:25<00:05, 27.37it/s]
Loading 0:  72%|███████▏  | 363/507 [00:25<00:04, 30.78it/s]
Loading 0:  72%|███████▏  | 367/507 [00:25<00:04, 30.56it/s]
Loading 0:  73%|███████▎  | 372/507 [00:25<00:03, 34.31it/s]
Loading 0:  74%|███████▍  | 376/507 [00:25<00:03, 34.02it/s]
Loading 0:  75%|███████▌  | 381/507 [00:25<00:03, 37.64it/s]
Loading 0:  76%|███████▌  | 386/507 [00:25<00:03, 38.31it/s]
Loading 0:  77%|███████▋  | 391/507 [00:25<00:03, 33.88it/s]
Loading 0:  78%|███████▊  | 395/507 [00:26<00:04, 26.05it/s]
Loading 0:  79%|███████▉  | 401/507 [00:26<00:03, 27.66it/s]
Loading 0:  80%|████████  | 406/507 [00:26<00:03, 31.92it/s]
Loading 0:  81%|████████  | 410/507 [00:26<00:03, 30.09it/s]
Loading 0:  82%|████████▏ | 417/507 [00:26<00:02, 37.41it/s]
Loading 0:  83%|████████▎ | 422/507 [00:26<00:02, 37.61it/s]
Loading 0:  84%|████████▍ | 427/507 [00:27<00:02, 37.76it/s]
Loading 0:  85%|████████▌ | 431/507 [00:27<00:02, 36.32it/s]
Loading 0:  86%|████████▌ | 436/507 [00:27<00:01, 37.57it/s]
Loading 0:  87%|████████▋ | 441/507 [00:27<00:01, 39.73it/s]
Loading 0:  88%|████████▊ | 446/507 [00:27<00:01, 33.39it/s]
Loading 0:  90%|████████▉ | 454/507 [00:27<00:01, 39.34it/s]
Loading 0:  91%|█████████ | 459/507 [00:30<00:06,  6.97it/s]
Loading 0:  92%|█████████▏| 465/507 [00:30<00:04,  9.35it/s]
Loading 0:  93%|█████████▎| 472/507 [00:30<00:02, 13.17it/s]
Loading 0:  94%|█████████▍| 476/507 [00:30<00:02, 15.18it/s]
Loading 0:  95%|█████████▍| 481/507 [00:30<00:01, 18.78it/s]
Loading 0:  96%|█████████▌| 486/507 [00:30<00:00, 22.13it/s]
Loading 0:  97%|█████████▋| 491/507 [00:30<00:00, 25.53it/s]
Loading 0:  98%|█████████▊| 496/507 [00:30<00:00, 29.29it/s]
Loading 0:  99%|█████████▉| 501/507 [00:31<00:00, 28.02it/s]
                                                            
Connection pool is full, discarding connection: %s. Connection pool size: %s
Job chaiml-small-espresso-an-6112-v5-mkmlizer completed after 128.28s with status: succeeded
Stopping job with name chaiml-small-espresso-an-6112-v5-mkmlizer
Pipeline stage MKMLizer completed in 131.26s
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-6112-v5
Waiting for inference service chaiml-small-espresso-an-6112-v5 to be ready
Inference service chaiml-small-espresso-an-6112-v5 ready after 184.28585004806519s
Pipeline stage MKMLDeployer completed in 186.34s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.377164840698242s
Received healthy response to inference request in 2.807579755783081s
Received healthy response to inference request in 2.787550926208496s
Received healthy response to inference request in 2.9720516204833984s
Received healthy response to inference request in 2.6172666549682617s
5 requests
0 failed requests
5th percentile: 2.6513235092163088
10th percentile: 2.6853803634643554
20th percentile: 2.753494071960449
30th percentile: 2.791556692123413
40th percentile: 2.799568223953247
50th percentile: 2.807579755783081
60th percentile: 2.873368501663208
70th percentile: 2.939157247543335
80th percentile: 3.053074264526367
90th percentile: 3.215119552612305
95th percentile: 3.2961421966552735
99th percentile: 3.3609603118896483
mean time: 2.912322759628296
Pipeline stage StressChecker completed in 15.92s
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 2.06s
Shutdown handler de-registered
chaiml-small-espresso-an_6112_v5 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 3306.64s
Shutdown handler de-registered
chaiml-small-espresso-an_6112_v5 status is now inactive due to auto deactivation removed underperforming models