chaiml-small-story-24112_3050

developer_uid: azuruce

submission_id: chaiml-small-story-24112_3050_v1

model_name: RPG-408-unsafe

model_group: ChaiML/small_story_24112

status: inactive

timestamp: 2024-11-21T07:32:52+00:00

num_battles: 10517

num_wins: 5216

celo_rating: 1244.78

family_friendly_score: 0.5622

family_friendly_standard_error: 0.007016140819567407

submission_type: basic

model_repo: ChaiML/small_story_241120_v1_all_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': 0.39281117040357744, 'latency_mean': 2.545678859949112, 'latency_p50': 2.5482324361801147, 'latency_p90': 2.8107223749160766}, {'batch_size': 3, 'throughput': 0.8224068324858409, 'latency_mean': 3.6320806837081907, 'latency_p50': 3.6329710483551025, 'latency_p90': 3.970711612701416}, {'batch_size': 5, 'throughput': 1.09324486316644, 'latency_mean': 4.547829185724258, 'latency_p50': 4.541969656944275, 'latency_p90': 5.074925565719605}, {'batch_size': 6, 'throughput': 1.1947586347877006, 'latency_mean': 4.9898663520812985, 'latency_p50': 4.984138607978821, 'latency_p90': 5.668527388572692}, {'batch_size': 8, 'throughput': 1.3221027968980295, 'latency_mean': 5.994601907730103, 'latency_p50': 6.000811696052551, 'latency_p90': 6.736478614807129}, {'batch_size': 10, 'throughput': 1.4046962934670626, 'latency_mean': 7.054142577648163, 'latency_p50': 7.054815411567688, 'latency_p90': 7.995854878425598}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: RPG-408-unsafe

is_internal_developer: True

language_model: ChaiML/small_story_241120_v1_all_albert

model_size: 22B

ranking_group: single

throughput_3p7s: 0.85

us_pacific_date: 2024-11-20

win_ratio: 0.495958923647428

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-24112-3050-v1-mkmlizer
Waiting for job on chaiml-small-story-24112-3050-v1-mkmlizer to finish
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-story-24112-3050-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-small-story-24112-3050-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-small-story-24112-3050-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-small-story-24112-3050-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-small-story-24112-3050-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-small-story-24112-3050-v1-mkmlizer: ║       /___/                                                         ║
chaiml-small-story-24112-3050-v1-mkmlizer: ║                                                                     ║
chaiml-small-story-24112-3050-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-small-story-24112-3050-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-small-story-24112-3050-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-small-story-24112-3050-v1-mkmlizer: ║                                                                     ║
chaiml-small-story-24112-3050-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-small-story-24112-3050-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-small-story-24112-3050-v1-mkmlizer: ║                                                                     ║
chaiml-small-story-24112-3050-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-small-story-24112-3050-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-small-story-24112-3050-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-small-story-24112-3050-v1-mkmlizer: ║                                                                     ║
chaiml-small-story-24112-3050-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-small-story-24112-3050-v1-mkmlizer: Downloaded to shared memory in 83.122s
chaiml-small-story-24112-3050-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmportz0xy4, device:0
chaiml-small-story-24112-3050-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-small-story-24112-3050-v1-mkmlizer: quantized model in 43.270s
chaiml-small-story-24112-3050-v1-mkmlizer: Processed model ChaiML/small_story_241120_v1_all_albert in 126.392s
chaiml-small-story-24112-3050-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-small-story-24112-3050-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-small-story-24112-3050-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-small-story-24112-3050-v1
chaiml-small-story-24112-3050-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-small-story-24112-3050-v1/config.json
chaiml-small-story-24112-3050-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-small-story-24112-3050-v1/special_tokens_map.json
chaiml-small-story-24112-3050-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-small-story-24112-3050-v1/tokenizer_config.json
chaiml-small-story-24112-3050-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-small-story-24112-3050-v1/tokenizer.json
chaiml-small-story-24112-3050-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-small-story-24112-3050-v1/flywheel_model.1.safetensors
chaiml-small-story-24112-3050-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-small-story-24112-3050-v1/flywheel_model.0.safetensors
chaiml-small-story-24112-3050-v1-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:19, 25.98it/s]
Loading 0:   2%|▏         | 12/507 [00:00<00:11, 41.71it/s]
Loading 0:   3%|▎         | 17/507 [00:00<00:12, 39.06it/s]
Loading 0:   4%|▍         | 22/507 [00:00<00:12, 39.42it/s]
Loading 0:   5%|▌         | 27/507 [00:00<00:11, 40.36it/s]
Loading 0:   6%|▋         | 32/507 [00:00<00:14, 33.46it/s]
Loading 0:   8%|▊         | 39/507 [00:01<00:11, 40.77it/s]
Loading 0:   9%|▊         | 44/507 [00:01<00:11, 40.53it/s]
Loading 0:  10%|▉         | 49/507 [00:01<00:13, 34.13it/s]
Loading 0:  10%|█         | 53/507 [00:01<00:17, 25.95it/s]
Loading 0:  11%|█         | 57/507 [00:01<00:17, 26.19it/s]
Loading 0:  12%|█▏        | 63/507 [00:01<00:14, 31.12it/s]
Loading 0:  13%|█▎        | 67/507 [00:01<00:13, 31.59it/s]
Loading 0:  14%|█▍        | 72/507 [00:02<00:12, 35.64it/s]
Loading 0:  15%|█▌        | 78/507 [00:02<00:10, 40.03it/s]
Loading 0:  16%|█▋        | 83/507 [00:02<00:11, 38.16it/s]
Loading 0:  17%|█▋        | 88/507 [00:02<00:11, 37.86it/s]
Loading 0:  18%|█▊        | 92/507 [00:02<00:11, 37.64it/s]
Loading 0:  19%|█▉        | 96/507 [00:02<00:11, 37.34it/s]
Loading 0:  20%|█▉        | 100/507 [00:02<00:11, 36.11it/s]
Loading 0:  21%|██        | 105/507 [00:02<00:10, 37.96it/s]
Loading 0:  21%|██▏       | 109/507 [00:03<00:11, 35.87it/s]
Loading 0:  22%|██▏       | 113/507 [00:03<00:15, 25.12it/s]
Loading 0:  23%|██▎       | 116/507 [00:03<00:16, 23.72it/s]
Loading 0:  24%|██▍       | 122/507 [00:03<00:14, 27.15it/s]
Loading 0:  25%|██▌       | 129/507 [00:03<00:11, 34.22it/s]
Loading 0:  26%|██▌       | 133/507 [00:03<00:10, 34.36it/s]
Loading 0:  27%|██▋       | 138/507 [00:04<00:09, 37.24it/s]
Loading 0:  28%|██▊       | 142/507 [00:04<00:10, 35.61it/s]
Loading 0:  29%|██▉       | 147/507 [00:04<00:09, 38.61it/s]
Loading 0:  30%|██▉       | 152/507 [00:04<00:09, 38.49it/s]
Loading 0:  31%|███       | 157/507 [00:04<00:08, 38.98it/s]
Loading 0:  32%|███▏      | 162/507 [00:04<00:08, 40.96it/s]
Loading 0:  33%|███▎      | 167/507 [00:04<00:08, 42.23it/s]
Loading 0:  34%|███▍      | 172/507 [00:05<00:12, 26.37it/s]
Loading 0:  35%|███▍      | 176/507 [00:05<00:12, 26.89it/s]
Loading 0:  36%|███▌      | 183/507 [00:05<00:09, 34.28it/s]
Loading 0:  37%|███▋      | 188/507 [00:05<00:09, 35.04it/s]
Loading 0:  38%|███▊      | 193/507 [00:05<00:08, 36.32it/s]
Loading 0:  39%|███▉      | 197/507 [00:05<00:08, 36.63it/s]
Loading 0:  40%|███▉      | 202/507 [00:05<00:08, 37.63it/s]
Loading 0:  41%|████      | 207/507 [00:05<00:07, 39.74it/s]
Loading 0:  42%|████▏     | 212/507 [00:06<00:08, 33.32it/s]
Loading 0:  43%|████▎     | 218/507 [00:06<00:07, 38.69it/s]
Loading 0:  44%|████▍     | 223/507 [00:06<00:08, 34.95it/s]
Loading 0:  45%|████▍     | 227/507 [00:06<00:09, 29.71it/s]
Loading 0:  46%|████▌     | 231/507 [00:06<00:09, 28.84it/s]
Loading 0:  47%|████▋     | 237/507 [00:06<00:08, 33.24it/s]
Loading 0:  48%|████▊     | 241/507 [00:07<00:08, 32.59it/s]
Loading 0:  49%|████▊     | 246/507 [00:07<00:07, 34.95it/s]
Loading 0:  49%|████▉     | 250/507 [00:07<00:07, 34.55it/s]
Loading 0:  50%|█████     | 255/507 [00:07<00:06, 36.74it/s]
Loading 0:  51%|█████     | 259/507 [00:07<00:06, 35.81it/s]
Loading 0:  52%|█████▏    | 264/507 [00:07<00:06, 37.68it/s]
Loading 0:  53%|█████▎    | 268/507 [00:07<00:06, 36.37it/s]
Loading 0:  54%|█████▍    | 273/507 [00:07<00:06, 38.69it/s]
Loading 0:  55%|█████▍    | 277/507 [00:08<00:06, 35.09it/s]
Loading 0:  56%|█████▌    | 282/507 [00:08<00:05, 37.87it/s]
Loading 0:  56%|█████▋    | 286/507 [00:08<00:08, 24.69it/s]
Loading 0:  57%|█████▋    | 290/507 [00:08<00:08, 26.67it/s]
Loading 0:  58%|█████▊    | 294/507 [00:08<00:07, 27.04it/s]
Loading 0:  59%|█████▉    | 299/507 [00:22<00:07, 27.04it/s]
Loading 0:  59%|█████▉    | 300/507 [00:22<03:11,  1.08it/s]
Loading 0:  60%|█████▉    | 302/507 [00:23<02:42,  1.26it/s]
Loading 0:  61%|██████    | 307/507 [00:23<01:45,  1.90it/s]
Loading 0:  61%|██████    | 310/507 [00:23<01:21,  2.41it/s]
Loading 0:  62%|██████▏   | 314/507 [00:23<00:57,  3.38it/s]
Loading 0:  63%|██████▎   | 319/507 [00:23<00:37,  5.00it/s]
Loading 0:  64%|██████▍   | 324/507 [00:23<00:25,  7.13it/s]
Loading 0:  65%|██████▍   | 328/507 [00:23<00:19,  9.14it/s]
Loading 0:  65%|██████▌   | 332/507 [00:23<00:15, 11.61it/s]
Loading 0:  66%|██████▋   | 337/507 [00:24<00:10, 15.50it/s]
Loading 0:  67%|██████▋   | 341/507 [00:24<00:10, 15.16it/s]
Loading 0:  68%|██████▊   | 345/507 [00:24<00:09, 17.82it/s]
Loading 0:  69%|██████▉   | 349/507 [00:24<00:07, 20.51it/s]
Loading 0:  70%|██████▉   | 354/507 [00:24<00:06, 25.13it/s]
Loading 0:  71%|███████   | 358/507 [00:24<00:05, 26.45it/s]
Loading 0:  72%|███████▏  | 363/507 [00:24<00:04, 30.24it/s]
Loading 0:  72%|███████▏  | 367/507 [00:25<00:04, 30.54it/s]
Loading 0:  73%|███████▎  | 372/507 [00:25<00:04, 33.50it/s]
Loading 0:  74%|███████▍  | 376/507 [00:25<00:03, 33.71it/s]
Loading 0:  75%|███████▌  | 381/507 [00:25<00:03, 37.09it/s]
Loading 0:  76%|███████▌  | 385/507 [00:25<00:03, 36.35it/s]
Loading 0:  77%|███████▋  | 389/507 [00:25<00:03, 36.80it/s]
Loading 0:  78%|███████▊  | 393/507 [00:25<00:03, 35.90it/s]
Loading 0:  78%|███████▊  | 397/507 [00:26<00:04, 26.22it/s]
Loading 0:  79%|███████▉  | 401/507 [00:26<00:04, 25.92it/s]
Loading 0:  80%|████████  | 408/507 [00:26<00:02, 33.01it/s]
Loading 0:  81%|████████▏ | 412/507 [00:26<00:02, 32.77it/s]
Loading 0:  82%|████████▏ | 417/507 [00:26<00:02, 35.51it/s]
Loading 0:  83%|████████▎ | 421/507 [00:26<00:02, 34.66it/s]
Loading 0:  84%|████████▍ | 426/507 [00:26<00:02, 37.39it/s]
Loading 0:  85%|████████▍ | 430/507 [00:26<00:02, 35.63it/s]
Loading 0:  86%|████████▌ | 435/507 [00:27<00:01, 38.34it/s]
Loading 0:  87%|████████▋ | 439/507 [00:27<00:01, 35.92it/s]
Loading 0:  88%|████████▊ | 444/507 [00:27<00:01, 37.60it/s]
Loading 0:  88%|████████▊ | 448/507 [00:27<00:01, 36.42it/s]
Loading 0:  90%|████████▉ | 454/507 [00:27<00:01, 37.10it/s]
Loading 0:  90%|█████████ | 458/507 [00:29<00:07,  6.24it/s]
Loading 0:  91%|█████████ | 461/507 [00:29<00:06,  7.51it/s]
Loading 0:  92%|█████████▏| 465/507 [00:29<00:04,  9.55it/s]
Loading 0:  93%|█████████▎| 472/507 [00:30<00:02, 14.73it/s]
Loading 0:  94%|█████████▍| 476/507 [00:30<00:01, 17.21it/s]
Loading 0:  95%|█████████▍| 481/507 [00:30<00:01, 21.25it/s]
Loading 0:  96%|█████████▌| 485/507 [00:30<00:00, 23.50it/s]
Loading 0:  97%|█████████▋| 490/507 [00:30<00:00, 27.47it/s]
Loading 0:  97%|█████████▋| 494/507 [00:30<00:00, 28.95it/s]
Loading 0:  98%|█████████▊| 499/507 [00:30<00:00, 32.21it/s]
Loading 0:  99%|█████████▉| 503/507 [00:30<00:00, 32.69it/s]
                                                            
Job chaiml-small-story-24112-3050-v1-mkmlizer completed after 156.0s with status: succeeded
Stopping job with name chaiml-small-story-24112-3050-v1-mkmlizer
Pipeline stage MKMLizer completed in 156.50s
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-story-24112-3050-v1
Waiting for inference service chaiml-small-story-24112-3050-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service chaiml-small-story-24112-3050-v1 ready after 211.446115732193s
Pipeline stage MKMLDeployer completed in 211.98s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.8265373706817627s
Received healthy response to inference request in 2.243710994720459s
Received healthy response to inference request in 2.2775824069976807s
Received healthy response to inference request in 2.2055788040161133s
Received healthy response to inference request in 2.303622007369995s
5 requests
0 failed requests
5th percentile: 2.2132052421569823
10th percentile: 2.2208316802978514
20th percentile: 2.23608455657959
30th percentile: 2.2504852771759034
40th percentile: 2.264033842086792
50th percentile: 2.2775824069976807
60th percentile: 2.2879982471466063
70th percentile: 2.2984140872955323
80th percentile: 2.408205080032349
90th percentile: 2.6173712253570556
95th percentile: 2.721954298019409
99th percentile: 2.805620756149292
mean time: 2.371406316757202
Pipeline stage StressChecker completed in 13.38s
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 2.38s
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 2.16s
Shutdown handler de-registered
chaiml-small-story-24112_3050_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 3083.03s
Shutdown handler de-registered
chaiml-small-story-24112_3050_v1 status is now inactive due to auto deactivation removed underperforming models