chaiml-espresso-story-24_3275

developer_uid: azuruce

submission_id: chaiml-espresso-story-24_3275_v2

model_name: chaiml-espresso-story-24_3275_v2

model_group: ChaiML/espresso_story_24

status: inactive

timestamp: 2024-12-06T01:42:56+00:00

num_battles: 8763

num_wins: 4252

celo_rating: 1252.61

family_friendly_score: 0.5826

family_friendly_standard_error: 0.006973911958148023

submission_type: basic

model_repo: ChaiML/espresso_story_241205_albert_v1_sft_2epoch_128alpha

model_architecture: MistralForCausalLM

model_num_parameters: 22247282688.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.3870213782112855, 'latency_mean': 2.5837752449512483, 'latency_p50': 2.584330916404724, 'latency_p90': 2.8673932552337646}, {'batch_size': 3, 'throughput': 0.8271434331882752, 'latency_mean': 3.618294144868851, 'latency_p50': 3.5830358266830444, 'latency_p90': 4.045796275138855}, {'batch_size': 5, 'throughput': 1.091341029004916, 'latency_mean': 4.560418683290481, 'latency_p50': 4.577722907066345, 'latency_p90': 5.150574159622193}, {'batch_size': 6, 'throughput': 1.1751118731744203, 'latency_mean': 5.05553569316864, 'latency_p50': 5.048677206039429, 'latency_p90': 5.737433934211731}, {'batch_size': 10, 'throughput': 1.4001271306077052, 'latency_mean': 7.080489718914032, 'latency_p50': 7.055447936058044, 'latency_p90': 8.046163082122803}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-espresso-story-24_3275_v2

is_internal_developer: True

language_model: ChaiML/espresso_story_241205_albert_v1_sft_2epoch_128alpha

model_size: 22B

ranking_group: single

throughput_3p7s: 0.86

us_pacific_date: 2024-12-05

win_ratio: 0.4852219559511583

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-espresso-story-24-3275-v2-mkmlizer
Waiting for job on chaiml-espresso-story-24-3275-v2-mkmlizer to finish
chaiml-espresso-story-24-3275-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-espresso-story-24-3275-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-espresso-story-24-3275-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-espresso-story-24-3275-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-espresso-story-24-3275-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-espresso-story-24-3275-v2-mkmlizer: ║       /___/                                                         ║
chaiml-espresso-story-24-3275-v2-mkmlizer: ║                                                                     ║
chaiml-espresso-story-24-3275-v2-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-espresso-story-24-3275-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-espresso-story-24-3275-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-espresso-story-24-3275-v2-mkmlizer: ║                                                                     ║
chaiml-espresso-story-24-3275-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-espresso-story-24-3275-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-espresso-story-24-3275-v2-mkmlizer: ║                                                                     ║
chaiml-espresso-story-24-3275-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-espresso-story-24-3275-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-espresso-story-24-3275-v2-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-espresso-story-24-3275-v2-mkmlizer: ║                                                                     ║
chaiml-espresso-story-24-3275-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-espresso-story-24-3275-v2-mkmlizer: Downloaded to shared memory in 59.749s
chaiml-espresso-story-24-3275-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpb6lbkri1, device:0
chaiml-espresso-story-24-3275-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-espresso-story-24-3275-v2-mkmlizer: quantized model in 46.767s
chaiml-espresso-story-24-3275-v2-mkmlizer: Processed model ChaiML/espresso_story_241205_albert_v1_sft_2epoch_128alpha in 106.516s
chaiml-espresso-story-24-3275-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-espresso-story-24-3275-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-espresso-story-24-3275-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-espresso-story-24-3275-v2
chaiml-espresso-story-24-3275-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-espresso-story-24-3275-v2/config.json
chaiml-espresso-story-24-3275-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-espresso-story-24-3275-v2/special_tokens_map.json
chaiml-espresso-story-24-3275-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-espresso-story-24-3275-v2/tokenizer_config.json
chaiml-espresso-story-24-3275-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-espresso-story-24-3275-v2/tokenizer.json
chaiml-espresso-story-24-3275-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-espresso-story-24-3275-v2/flywheel_model.1.safetensors
chaiml-espresso-story-24-3275-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-espresso-story-24-3275-v2/flywheel_model.0.safetensors
chaiml-espresso-story-24-3275-v2-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:22, 22.10it/s]
Loading 0:   2%|▏         | 10/507 [00:00<00:15, 31.71it/s]
Loading 0:   3%|▎         | 14/507 [00:00<00:18, 27.34it/s]
Loading 0:   4%|▎         | 19/507 [00:00<00:14, 32.69it/s]
Loading 0:   5%|▍         | 23/507 [00:00<00:16, 28.91it/s]
Loading 0:   6%|▌         | 28/507 [00:00<00:14, 32.34it/s]
Loading 0:   6%|▋         | 32/507 [00:01<00:16, 28.56it/s]
Loading 0:   7%|▋         | 37/507 [00:01<00:14, 32.98it/s]
Loading 0:   8%|▊         | 41/507 [00:01<00:16, 28.74it/s]
Loading 0:   9%|▉         | 46/507 [00:01<00:13, 33.20it/s]
Loading 0:  10%|▉         | 50/507 [00:01<00:15, 30.02it/s]
Loading 0:  11%|█         | 54/507 [00:02<00:22, 20.51it/s]
Loading 0:  11%|█         | 57/507 [00:02<00:21, 20.56it/s]
Loading 0:  12%|█▏        | 61/507 [00:02<00:18, 23.55it/s]
Loading 0:  13%|█▎        | 65/507 [00:02<00:19, 22.21it/s]
Loading 0:  14%|█▍        | 70/507 [00:02<00:16, 26.96it/s]
Loading 0:  15%|█▍        | 75/507 [00:02<00:14, 30.01it/s]
Loading 0:  16%|█▌        | 80/507 [00:02<00:14, 29.60it/s]
Loading 0:  17%|█▋        | 85/507 [00:03<00:12, 33.16it/s]
Loading 0:  18%|█▊        | 89/507 [00:03<00:14, 29.83it/s]
Loading 0:  19%|█▉        | 96/507 [00:03<00:11, 35.70it/s]
Loading 0:  20%|█▉        | 100/507 [00:03<00:12, 33.58it/s]
Loading 0:  21%|██        | 104/507 [00:03<00:11, 34.21it/s]
Loading 0:  21%|██▏       | 108/507 [00:03<00:13, 30.63it/s]
Loading 0:  22%|██▏       | 113/507 [00:04<00:15, 24.65it/s]
Loading 0:  23%|██▎       | 116/507 [00:04<00:16, 23.19it/s]
Loading 0:  24%|██▍       | 122/507 [00:04<00:14, 27.00it/s]
Loading 0:  25%|██▌       | 129/507 [00:04<00:11, 33.46it/s]
Loading 0:  26%|██▌       | 133/507 [00:04<00:11, 31.95it/s]
Loading 0:  27%|██▋       | 138/507 [00:04<00:10, 34.17it/s]
Loading 0:  28%|██▊       | 142/507 [00:04<00:11, 32.49it/s]
Loading 0:  29%|██▉       | 147/507 [00:05<00:10, 34.09it/s]
Loading 0:  30%|██▉       | 151/507 [00:05<00:10, 32.65it/s]
Loading 0:  31%|███       | 156/507 [00:05<00:09, 35.62it/s]
Loading 0:  32%|███▏      | 160/507 [00:05<00:10, 34.00it/s]
Loading 0:  32%|███▏      | 164/507 [00:05<00:10, 33.74it/s]
Loading 0:  33%|███▎      | 169/507 [00:05<00:12, 26.17it/s]
Loading 0:  34%|███▍      | 172/507 [00:05<00:13, 25.30it/s]
Loading 0:  35%|███▍      | 176/507 [00:06<00:13, 24.73it/s]
Loading 0:  36%|███▌      | 181/507 [00:06<00:11, 29.07it/s]
Loading 0:  36%|███▋      | 185/507 [00:06<00:11, 26.96it/s]
Loading 0:  37%|███▋      | 190/507 [00:06<00:10, 31.17it/s]
Loading 0:  38%|███▊      | 194/507 [00:06<00:11, 28.42it/s]
Loading 0:  39%|███▉      | 199/507 [00:06<00:09, 31.54it/s]
Loading 0:  40%|████      | 203/507 [00:06<00:10, 28.94it/s]
Loading 0:  41%|████      | 208/507 [00:07<00:08, 33.58it/s]
Loading 0:  42%|████▏     | 212/507 [00:07<00:09, 30.10it/s]
Loading 0:  43%|████▎     | 217/507 [00:07<00:08, 34.04it/s]
Loading 0:  44%|████▎     | 221/507 [00:07<00:09, 30.88it/s]
Loading 0:  44%|████▍     | 225/507 [00:07<00:12, 22.08it/s]
Loading 0:  45%|████▌     | 230/507 [00:07<00:11, 24.03it/s]
Loading 0:  46%|████▋     | 235/507 [00:08<00:09, 28.49it/s]
Loading 0:  47%|████▋     | 239/507 [00:08<00:10, 25.98it/s]
Loading 0:  48%|████▊     | 244/507 [00:08<00:08, 30.03it/s]
Loading 0:  49%|████▉     | 248/507 [00:08<00:09, 27.69it/s]
Loading 0:  50%|████▉     | 253/507 [00:08<00:08, 31.69it/s]
Loading 0:  51%|█████     | 257/507 [00:08<00:08, 28.36it/s]
Loading 0:  52%|█████▏    | 262/507 [00:08<00:07, 32.19it/s]
Loading 0:  52%|█████▏    | 266/507 [00:09<00:08, 28.91it/s]
Loading 0:  53%|█████▎    | 271/507 [00:09<00:07, 32.55it/s]
Loading 0:  54%|█████▍    | 275/507 [00:09<00:07, 29.36it/s]
Loading 0:  55%|█████▌    | 280/507 [00:09<00:06, 33.11it/s]
Loading 0:  56%|█████▌    | 284/507 [00:09<00:09, 23.67it/s]
Loading 0:  57%|█████▋    | 287/507 [00:10<00:10, 21.08it/s]
Loading 0:  58%|█████▊    | 293/507 [00:10<00:08, 24.15it/s]
Loading 0:  59%|█████▉    | 298/507 [00:10<00:07, 28.57it/s]
Loading 0:  60%|█████▉    | 302/507 [00:25<03:35,  1.05s/it]
Loading 0:  61%|██████    | 307/507 [00:25<02:24,  1.38it/s]
Loading 0:  61%|██████▏   | 311/507 [00:26<01:46,  1.84it/s]
Loading 0:  62%|██████▏   | 316/507 [00:26<01:11,  2.67it/s]
Loading 0:  63%|██████▎   | 320/507 [00:26<00:53,  3.51it/s]
Loading 0:  64%|██████▍   | 325/507 [00:26<00:36,  5.03it/s]
Loading 0:  65%|██████▍   | 329/507 [00:26<00:27,  6.40it/s]
Loading 0:  66%|██████▌   | 334/507 [00:26<00:19,  8.94it/s]
Loading 0:  67%|██████▋   | 339/507 [00:26<00:14, 11.79it/s]
Loading 0:  68%|██████▊   | 343/507 [00:27<00:14, 11.70it/s]
Loading 0:  68%|██████▊   | 347/507 [00:27<00:11, 13.44it/s]
Loading 0:  69%|██████▉   | 352/507 [00:27<00:08, 17.67it/s]
Loading 0:  70%|███████   | 356/507 [00:27<00:08, 18.83it/s]
Loading 0:  71%|███████   | 361/507 [00:27<00:06, 23.13it/s]
Loading 0:  72%|███████▏  | 365/507 [00:28<00:06, 22.96it/s]
Loading 0:  73%|███████▎  | 370/507 [00:28<00:05, 27.15it/s]
Loading 0:  74%|███████▍  | 374/507 [00:28<00:05, 26.30it/s]
Loading 0:  75%|███████▌  | 381/507 [00:28<00:03, 34.07it/s]
Loading 0:  76%|███████▌  | 386/507 [00:28<00:03, 34.96it/s]
Loading 0:  77%|███████▋  | 390/507 [00:28<00:03, 29.43it/s]
Loading 0:  78%|███████▊  | 394/507 [00:28<00:03, 31.47it/s]
Loading 0:  79%|███████▊  | 398/507 [00:29<00:04, 26.29it/s]
Loading 0:  79%|███████▉  | 402/507 [00:29<00:04, 25.45it/s]
Loading 0:  80%|████████  | 406/507 [00:29<00:03, 28.34it/s]
Loading 0:  81%|████████  | 410/507 [00:29<00:03, 25.89it/s]
Loading 0:  82%|████████▏ | 415/507 [00:29<00:03, 30.64it/s]
Loading 0:  83%|████████▎ | 419/507 [00:29<00:03, 27.42it/s]
Loading 0:  84%|████████▎ | 424/507 [00:29<00:02, 31.48it/s]
Loading 0:  84%|████████▍ | 428/507 [00:30<00:02, 28.91it/s]
Loading 0:  85%|████████▌ | 433/507 [00:30<00:02, 33.31it/s]
Loading 0:  86%|████████▌ | 437/507 [00:30<00:02, 30.65it/s]
Loading 0:  88%|████████▊ | 444/507 [00:30<00:01, 37.60it/s]
Loading 0:  89%|████████▊ | 449/507 [00:30<00:01, 37.18it/s]
Loading 0:  90%|████████▉ | 454/507 [00:30<00:01, 36.17it/s]
Loading 0:  90%|█████████ | 458/507 [00:33<00:07,  6.13it/s]
Loading 0:  91%|█████████ | 461/507 [00:33<00:06,  7.31it/s]
Loading 0:  92%|█████████▏| 465/507 [00:33<00:04,  9.25it/s]
Loading 0:  93%|█████████▎| 472/507 [00:33<00:02, 14.18it/s]
Loading 0:  94%|█████████▍| 476/507 [00:33<00:01, 16.44it/s]
Loading 0:  95%|█████████▍| 481/507 [00:33<00:01, 20.36it/s]
Loading 0:  96%|█████████▌| 485/507 [00:33<00:00, 22.49it/s]
Loading 0:  97%|█████████▋| 490/507 [00:33<00:00, 26.41it/s]
Loading 0:  97%|█████████▋| 494/507 [00:34<00:00, 27.38it/s]
Loading 0:  98%|█████████▊| 499/507 [00:34<00:00, 30.63it/s]
Loading 0:  99%|█████████▉| 503/507 [00:34<00:00, 30.82it/s]
                                                            
Job chaiml-espresso-story-24-3275-v2-mkmlizer completed after 136.32s with status: succeeded
Stopping job with name chaiml-espresso-story-24-3275-v2-mkmlizer
Pipeline stage MKMLizer completed in 137.91s
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-story-24-3275-v2
Waiting for inference service chaiml-espresso-story-24-3275-v2 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
Failed to get response for submission blend_jikul_2024-11-25: ('http://blend-sigim-2024-11-25-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '{"detail":"Gateway Timeout"}')
Inference service chaiml-espresso-story-24-3275-v2 ready after 198.8044068813324s
Pipeline stage MKMLDeployer completed in 201.16s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.765970468521118s
Received healthy response to inference request in 2.423502206802368s
Received healthy response to inference request in 2.421793222427368s
Received healthy response to inference request in 2.301682472229004s
Received healthy response to inference request in 2.331347703933716s
5 requests
0 failed requests
5th percentile: 2.3076155185699463
10th percentile: 2.3135485649108887
20th percentile: 2.3254146575927734
30th percentile: 2.349436807632446
40th percentile: 2.385615015029907
50th percentile: 2.421793222427368
60th percentile: 2.422476816177368
70th percentile: 2.4231604099273683
80th percentile: 2.4919958591461184
90th percentile: 2.628983163833618
95th percentile: 2.697476816177368
99th percentile: 2.752271738052368
mean time: 2.448859214782715
Pipeline stage StressChecker completed in 13.97s
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 2.15s
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 2.11s
Shutdown handler de-registered
chaiml-espresso-story-24_3275_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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-espresso-story-24-3275-v2-profiler
Waiting for inference service chaiml-espresso-story-24-3275-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 3063.32s
Shutdown handler de-registered
chaiml-espresso-story-24_3275_v2 status is now inactive due to auto deactivation removed underperforming models