chaiml-small-story-24112_8710

developer_uid: azuruce

submission_id: chaiml-small-story-24112_8710_v1

model_name: ant_rank_bottom_fixed

model_group: ChaiML/small_story_24112

status: inactive

timestamp: 2024-11-22T13:19:42+00:00

num_battles: 17748

num_wins: 8488

celo_rating: 1234.38

family_friendly_score: 0.5594

family_friendly_standard_error: 0.007020991952708677

submission_type: basic

model_repo: ChaiML/small_story_241120_v4_safe_albert

model_architecture: MistralForCausalLM

model_num_parameters: 22247282688.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.38959074163708574, 'latency_mean': 2.5667012774944307, 'latency_p50': 2.5628339052200317, 'latency_p90': 2.8494143962860106}, {'batch_size': 3, 'throughput': 0.8354184149793201, 'latency_mean': 3.58304998755455, 'latency_p50': 3.5620665550231934, 'latency_p90': 3.944514942169189}, {'batch_size': 5, 'throughput': 1.1041105845444583, 'latency_mean': 4.517097327709198, 'latency_p50': 4.548037886619568, 'latency_p90': 5.070700287818909}, {'batch_size': 6, 'throughput': 1.1867147569515684, 'latency_mean': 5.022061264514923, 'latency_p50': 5.003165364265442, 'latency_p90': 5.714530611038208}, {'batch_size': 10, 'throughput': 1.4105909121562317, 'latency_mean': 7.036504836082458, 'latency_p50': 6.998459219932556, 'latency_p90': 7.9714240550994875}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: ant_rank_bottom_fixed

is_internal_developer: True

language_model: ChaiML/small_story_241120_v4_safe_albert

model_size: 22B

ranking_group: single

throughput_3p7s: 0.88

us_pacific_date: 2024-11-22

win_ratio: 0.4782510705431598

generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, '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-small-story-24112-8710-v1-mkmlizer
Waiting for job on chaiml-small-story-24112-8710-v1-mkmlizer to finish
chaiml-small-story-24112-8710-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-small-story-24112-8710-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-small-story-24112-8710-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-small-story-24112-8710-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-small-story-24112-8710-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-small-story-24112-8710-v1-mkmlizer: ║       /___/                                                         ║
chaiml-small-story-24112-8710-v1-mkmlizer: ║                                                                     ║
chaiml-small-story-24112-8710-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-small-story-24112-8710-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-small-story-24112-8710-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-small-story-24112-8710-v1-mkmlizer: ║                                                                     ║
chaiml-small-story-24112-8710-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-small-story-24112-8710-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-small-story-24112-8710-v1-mkmlizer: ║                                                                     ║
chaiml-small-story-24112-8710-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-small-story-24112-8710-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-small-story-24112-8710-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-small-story-24112-8710-v1-mkmlizer: ║                                                                     ║
chaiml-small-story-24112-8710-v1-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
Failed to get response for submission jic062-dpo-v3-0-nemo_v1: ('http://jic062-dpo-v3-0-nemo-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
chaiml-small-story-24112-8710-v1-mkmlizer: Downloaded to shared memory in 86.275s
chaiml-small-story-24112-8710-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpel318f0x, device:0
chaiml-small-story-24112-8710-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-small-story-24112-8710-v1-mkmlizer: quantized model in 43.220s
chaiml-small-story-24112-8710-v1-mkmlizer: Processed model ChaiML/small_story_241120_v4_safe_albert in 129.495s
chaiml-small-story-24112-8710-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-small-story-24112-8710-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-small-story-24112-8710-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-small-story-24112-8710-v1
chaiml-small-story-24112-8710-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-small-story-24112-8710-v1/config.json
chaiml-small-story-24112-8710-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-small-story-24112-8710-v1/special_tokens_map.json
chaiml-small-story-24112-8710-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-small-story-24112-8710-v1/tokenizer_config.json
chaiml-small-story-24112-8710-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-small-story-24112-8710-v1/tokenizer.json
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-small-story-24112-8710-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-small-story-24112-8710-v1/flywheel_model.1.safetensors
chaiml-small-story-24112-8710-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-small-story-24112-8710-v1/flywheel_model.0.safetensors
chaiml-small-story-24112-8710-v1-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:19, 25.17it/s]
Loading 0:   2%|▏         | 12/507 [00:00<00:12, 40.32it/s]
Loading 0:   3%|▎         | 17/507 [00:00<00:12, 38.24it/s]
Loading 0:   4%|▍         | 22/507 [00:00<00:12, 39.08it/s]
Loading 0:   5%|▌         | 27/507 [00:00<00:11, 40.50it/s]
Loading 0:   6%|▋         | 32/507 [00:00<00:14, 32.03it/s]
Loading 0:   7%|▋         | 37/507 [00:01<00:13, 35.32it/s]
Loading 0:   8%|▊         | 41/507 [00:01<00:15, 30.97it/s]
Loading 0:   9%|▉         | 46/507 [00:01<00:13, 35.28it/s]
Loading 0:  10%|▉         | 50/507 [00:01<00:14, 32.01it/s]
Loading 0:  11%|█         | 54/507 [00:01<00:18, 24.35it/s]
Loading 0:  11%|█         | 57/507 [00:01<00:18, 24.33it/s]
Loading 0:  12%|█▏        | 63/507 [00:01<00:14, 30.13it/s]
Loading 0:  13%|█▎        | 67/507 [00:02<00:14, 30.57it/s]
Loading 0:  14%|█▍        | 73/507 [00:02<00:13, 33.33it/s]
Loading 0:  16%|█▌        | 80/507 [00:02<00:12, 35.31it/s]
Loading 0:  17%|█▋        | 87/507 [00:02<00:10, 40.91it/s]
Loading 0:  18%|█▊        | 92/507 [00:02<00:10, 38.64it/s]
Loading 0:  19%|█▉        | 96/507 [00:02<00:10, 38.00it/s]
Loading 0:  20%|█▉        | 100/507 [00:02<00:11, 36.02it/s]
Loading 0:  21%|██        | 105/507 [00:03<00:10, 37.81it/s]
Loading 0:  21%|██▏       | 109/507 [00:03<00:11, 35.10it/s]
Loading 0:  22%|██▏       | 113/507 [00:03<00:14, 27.18it/s]
Loading 0:  23%|██▎       | 116/507 [00:03<00:16, 24.30it/s]
Loading 0:  24%|██▍       | 122/507 [00:03<00:13, 27.90it/s]
Loading 0:  25%|██▌       | 129/507 [00:03<00:11, 34.22it/s]
Loading 0:  26%|██▌       | 133/507 [00:04<00:11, 33.12it/s]
Loading 0:  27%|██▋       | 138/507 [00:04<00:10, 35.45it/s]
Loading 0:  28%|██▊       | 142/507 [00:04<00:10, 34.07it/s]
Loading 0:  29%|██▉       | 147/507 [00:04<00:09, 37.04it/s]
Loading 0:  30%|██▉       | 151/507 [00:04<00:09, 36.34it/s]
Loading 0:  31%|███       | 156/507 [00:04<00:08, 39.46it/s]
Loading 0:  32%|███▏      | 161/507 [00:04<00:08, 38.46it/s]
Loading 0:  33%|███▎      | 166/507 [00:04<00:08, 40.79it/s]
Loading 0:  34%|███▎      | 171/507 [00:05<00:12, 26.53it/s]
Loading 0:  35%|███▍      | 176/507 [00:05<00:11, 28.10it/s]
Loading 0:  36%|███▌      | 183/507 [00:05<00:09, 35.08it/s]
Loading 0:  37%|███▋      | 188/507 [00:05<00:08, 35.47it/s]
Loading 0:  38%|███▊      | 193/507 [00:05<00:08, 37.17it/s]
Loading 0:  39%|███▉      | 198/507 [00:05<00:07, 39.35it/s]
Loading 0:  40%|████      | 203/507 [00:06<00:08, 34.82it/s]
Loading 0:  41%|████▏     | 210/507 [00:06<00:06, 42.60it/s]
Loading 0:  42%|████▏     | 215/507 [00:06<00:06, 42.13it/s]
Loading 0:  43%|████▎     | 220/507 [00:06<00:07, 37.20it/s]
Loading 0:  44%|████▍     | 225/507 [00:06<00:09, 29.40it/s]
Loading 0:  45%|████▌     | 230/507 [00:06<00:09, 29.27it/s]
Loading 0:  47%|████▋     | 237/507 [00:06<00:07, 34.83it/s]
Loading 0:  48%|████▊     | 241/507 [00:07<00:07, 34.80it/s]
Loading 0:  49%|████▊     | 246/507 [00:07<00:07, 37.19it/s]
Loading 0:  49%|████▉     | 250/507 [00:07<00:07, 36.44it/s]
Loading 0:  50%|█████     | 255/507 [00:07<00:06, 38.73it/s]
Loading 0:  51%|█████▏    | 260/507 [00:07<00:06, 38.92it/s]
Loading 0:  52%|█████▏    | 265/507 [00:07<00:06, 39.50it/s]
Loading 0:  53%|█████▎    | 270/507 [00:07<00:05, 40.78it/s]
Loading 0:  54%|█████▍    | 275/507 [00:07<00:06, 35.37it/s]
Loading 0:  56%|█████▌    | 283/507 [00:08<00:05, 41.07it/s]
Loading 0:  57%|█████▋    | 288/507 [00:08<00:07, 28.76it/s]
Loading 0:  58%|█████▊    | 293/507 [00:08<00:07, 29.40it/s]
Loading 0:  59%|█████▉    | 299/507 [00:23<00:07, 29.40it/s]
Loading 0:  59%|█████▉    | 300/507 [00:23<02:40,  1.29it/s]
Loading 0:  60%|█████▉    | 302/507 [00:23<02:20,  1.46it/s]
Loading 0:  61%|██████    | 307/507 [00:23<01:36,  2.08it/s]
Loading 0:  61%|██████    | 310/507 [00:23<01:16,  2.56it/s]
Loading 0:  62%|██████▏   | 314/507 [00:23<00:55,  3.49it/s]
Loading 0:  63%|██████▎   | 319/507 [00:24<00:37,  5.07it/s]
Loading 0:  64%|██████▍   | 324/507 [00:24<00:25,  7.15it/s]
Loading 0:  65%|██████▍   | 328/507 [00:24<00:19,  9.17it/s]
Loading 0:  65%|██████▌   | 332/507 [00:24<00:14, 11.68it/s]
Loading 0:  66%|██████▋   | 337/507 [00:24<00:10, 15.64it/s]
Loading 0:  67%|██████▋   | 342/507 [00:24<00:11, 14.79it/s]
Loading 0:  68%|██████▊   | 347/507 [00:25<00:08, 17.93it/s]
Loading 0:  70%|██████▉   | 354/507 [00:25<00:06, 24.70it/s]
Loading 0:  71%|███████   | 359/507 [00:25<00:05, 27.47it/s]
Loading 0:  72%|███████▏  | 364/507 [00:25<00:04, 30.35it/s]
Loading 0:  73%|███████▎  | 369/507 [00:25<00:04, 32.13it/s]
Loading 0:  74%|███████▎  | 373/507 [00:25<00:04, 33.25it/s]
Loading 0:  75%|███████▍  | 379/507 [00:25<00:03, 35.48it/s]
Loading 0:  76%|███████▌  | 383/507 [00:25<00:03, 32.71it/s]
Loading 0:  77%|███████▋  | 389/507 [00:26<00:03, 37.80it/s]
Loading 0:  78%|███████▊  | 394/507 [00:26<00:03, 34.06it/s]
Loading 0:  79%|███████▊  | 398/507 [00:26<00:03, 29.96it/s]
Loading 0:  79%|███████▉  | 402/507 [00:26<00:03, 28.94it/s]
Loading 0:  80%|████████  | 408/507 [00:26<00:02, 33.62it/s]
Loading 0:  81%|████████▏ | 412/507 [00:26<00:02, 32.98it/s]
Loading 0:  82%|████████▏ | 417/507 [00:26<00:02, 35.39it/s]
Loading 0:  83%|████████▎ | 421/507 [00:27<00:02, 34.07it/s]
Loading 0:  84%|████████▍ | 426/507 [00:27<00:02, 37.36it/s]
Loading 0:  85%|████████▍ | 430/507 [00:27<00:02, 35.75it/s]
Loading 0:  86%|████████▌ | 435/507 [00:27<00:01, 38.47it/s]
Loading 0:  87%|████████▋ | 439/507 [00:27<00:01, 37.28it/s]
Loading 0:  88%|████████▊ | 444/507 [00:27<00:01, 40.37it/s]
Loading 0:  89%|████████▊ | 449/507 [00:27<00:01, 40.04it/s]
Loading 0:  90%|████████▉ | 454/507 [00:27<00:01, 38.76it/s]
Loading 0:  90%|█████████ | 458/507 [00:30<00:08,  6.01it/s]
Loading 0:  91%|█████████ | 461/507 [00:30<00:06,  7.21it/s]
Loading 0:  92%|█████████▏| 465/507 [00:30<00:04,  9.23it/s]
Loading 0:  93%|█████████▎| 472/507 [00:30<00:02, 14.02it/s]
Loading 0:  94%|█████████▍| 476/507 [00:30<00:01, 16.43it/s]
Loading 0:  95%|█████████▍| 481/507 [00:30<00:01, 20.70it/s]
Loading 0:  96%|█████████▌| 485/507 [00:30<00:00, 22.45it/s]
Loading 0:  97%|█████████▋| 490/507 [00:31<00:00, 26.37it/s]
Loading 0:  97%|█████████▋| 494/507 [00:31<00:00, 27.20it/s]
Loading 0:  98%|█████████▊| 499/507 [00:31<00:00, 30.49it/s]
Loading 0:  99%|█████████▉| 503/507 [00:31<00:00, 31.05it/s]
                                                            
Job chaiml-small-story-24112-8710-v1-mkmlizer completed after 156.46s with status: succeeded
Stopping job with name chaiml-small-story-24112-8710-v1-mkmlizer
Pipeline stage MKMLizer completed in 157.11s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-small-story-24112-8710-v1
Waiting for inference service chaiml-small-story-24112-8710-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
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
Inference service chaiml-small-story-24112-8710-v1 ready after 230.87996125221252s
Pipeline stage MKMLDeployer completed in 231.42s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.973679780960083s
Received healthy response to inference request in 2.292576551437378s
Received healthy response to inference request in 2.9915125370025635s
Received healthy response to inference request in 2.347781181335449s
Received healthy response to inference request in 2.3164825439453125s
5 requests
0 failed requests
5th percentile: 2.297357749938965
10th percentile: 2.3021389484405517
20th percentile: 2.3117013454437254
30th percentile: 2.3227422714233397
40th percentile: 2.3352617263793944
50th percentile: 2.347781181335449
60th percentile: 2.5981406211853026
70th percentile: 2.848500061035156
80th percentile: 2.977246332168579
90th percentile: 2.984379434585571
95th percentile: 2.9879459857940676
99th percentile: 2.9907992267608643
mean time: 2.584406518936157
Pipeline stage StressChecker completed in 14.52s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%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
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 5.49s
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 2.14s
Shutdown handler de-registered
chaiml-small-story-24112_8710_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 3473.81s
Shutdown handler de-registered
chaiml-small-story-24112_8710_v1 status is now inactive due to auto deactivation removed underperforming models