chaiml-lexical-viral-v5a_2693

developer_uid: zonemercy

submission_id: chaiml-lexical-viral-v5a_2693_v4

model_name: tempv1-1

model_group: ChaiML/Lexical-Viral-v5a

status: torndown

timestamp: 2024-12-11T09:04:04+00:00

num_battles: 9318

num_wins: 4772

celo_rating: 1273.89

family_friendly_score: 0.5800000000000001

family_friendly_standard_error: 0.006979971346646059

submission_type: basic

model_repo: ChaiML/Lexical-Viral-v5ava-12b01e5r128

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.6165563085997723, 'latency_mean': 1.6218545269966125, 'latency_p50': 1.6121268272399902, 'latency_p90': 1.7957191705703734}, {'batch_size': 3, 'throughput': 1.1161150545426837, 'latency_mean': 2.677237972021103, 'latency_p50': 2.651526689529419, 'latency_p90': 2.9689801692962647}, {'batch_size': 5, 'throughput': 1.3382562918429832, 'latency_mean': 3.7072873055934905, 'latency_p50': 3.7181458473205566, 'latency_p90': 4.214781332015991}, {'batch_size': 6, 'throughput': 1.4041546157989504, 'latency_mean': 4.25360957980156, 'latency_p50': 4.261310815811157, 'latency_p90': 4.732959151268005}, {'batch_size': 8, 'throughput': 1.477294057253693, 'latency_mean': 5.385617979764938, 'latency_p50': 5.408448100090027, 'latency_p90': 6.063175535202026}, {'batch_size': 10, 'throughput': 1.510055515359732, 'latency_mean': 6.559119676351547, 'latency_p50': 6.5745813846588135, 'latency_p90': 7.413880705833435}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: tempv1-1

is_internal_developer: True

language_model: ChaiML/Lexical-Viral-v5ava-12b01e5r128

model_size: 13B

ranking_group: single

throughput_3p7s: 1.35

us_pacific_date: 2024-12-11

win_ratio: 0.5121270658939686

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', '<|eot_id|>', '<|im_end|>', '</s>', 'You:', 'User:', 'Bot:'], '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-lexical-viral-v5a-2693-v4-mkmlizer
Waiting for job on chaiml-lexical-viral-v5a-2693-v4-mkmlizer to finish
chaiml-lexical-viral-v5a-2693-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-lexical-viral-v5a-2693-v4-mkmlizer: ║     _____            __           __                                ║
chaiml-lexical-viral-v5a-2693-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-lexical-viral-v5a-2693-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-lexical-viral-v5a-2693-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-lexical-viral-v5a-2693-v4-mkmlizer: ║       /___/                                                         ║
chaiml-lexical-viral-v5a-2693-v4-mkmlizer: ║                                                                     ║
chaiml-lexical-viral-v5a-2693-v4-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-lexical-viral-v5a-2693-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-lexical-viral-v5a-2693-v4-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-lexical-viral-v5a-2693-v4-mkmlizer: ║                                                                     ║
chaiml-lexical-viral-v5a-2693-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-lexical-viral-v5a-2693-v4-mkmlizer: ║  belonging to:                                                      ║
chaiml-lexical-viral-v5a-2693-v4-mkmlizer: ║                                                                     ║
chaiml-lexical-viral-v5a-2693-v4-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-lexical-viral-v5a-2693-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-lexical-viral-v5a-2693-v4-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-lexical-viral-v5a-2693-v4-mkmlizer: ║                                                                     ║
chaiml-lexical-viral-v5a-2693-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-lexical-viral-v5a-2693-v4-mkmlizer: Downloaded to shared memory in 34.740s
chaiml-lexical-viral-v5a-2693-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpu16dv35m, device:0
chaiml-lexical-viral-v5a-2693-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-lexical-viral-v5a-2693-v4-mkmlizer: quantized model in 40.046s
chaiml-lexical-viral-v5a-2693-v4-mkmlizer: Processed model ChaiML/Lexical-Viral-v5ava-12b01e5r128 in 74.786s
chaiml-lexical-viral-v5a-2693-v4-mkmlizer: creating bucket guanaco-mkml-models
chaiml-lexical-viral-v5a-2693-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-lexical-viral-v5a-2693-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-lexical-viral-v5a-2693-v4
chaiml-lexical-viral-v5a-2693-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-lexical-viral-v5a-2693-v4/config.json
chaiml-lexical-viral-v5a-2693-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-lexical-viral-v5a-2693-v4/special_tokens_map.json
chaiml-lexical-viral-v5a-2693-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-lexical-viral-v5a-2693-v4/tokenizer_config.json
chaiml-lexical-viral-v5a-2693-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-lexical-viral-v5a-2693-v4/tokenizer.json
chaiml-lexical-viral-v5a-2693-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-lexical-viral-v5a-2693-v4/flywheel_model.0.safetensors
chaiml-lexical-viral-v5a-2693-v4-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.32it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:09, 36.79it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:09, 37.15it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:08, 38.11it/s]
Loading 0:   7%|▋         | 27/363 [00:00<00:08, 39.71it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:10, 31.21it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:09, 34.39it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:10, 30.73it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:09, 35.05it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:09, 32.47it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:08, 36.84it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:08, 37.46it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:13, 21.50it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:11, 25.77it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:11, 25.58it/s]
Loading 0:  21%|██▏       | 78/363 [00:02<00:09, 30.33it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:09, 28.91it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:08, 33.03it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:09, 30.21it/s]
Loading 0:  26%|██▋       | 96/363 [00:03<00:08, 32.73it/s]
Loading 0:  28%|██▊       | 100/363 [00:03<00:08, 29.95it/s]
Loading 0:  29%|██▉       | 105/363 [00:03<00:07, 33.86it/s]
Loading 0:  30%|███       | 110/363 [00:03<00:07, 35.37it/s]
Loading 0:  31%|███▏      | 114/363 [00:03<00:07, 33.26it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:08, 30.18it/s]
Loading 0:  34%|███▍      | 123/363 [00:03<00:07, 33.94it/s]
Loading 0:  35%|███▍      | 127/363 [00:04<00:07, 30.90it/s]
Loading 0:  36%|███▋      | 132/363 [00:04<00:06, 34.85it/s]
Loading 0:  37%|███▋      | 136/363 [00:04<00:07, 31.42it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:08, 26.43it/s]
Loading 0:  40%|███▉      | 145/363 [00:04<00:08, 26.00it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:08, 25.12it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:06, 32.83it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:06, 32.66it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:05, 36.14it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:05, 35.29it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:04, 38.27it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 36.02it/s]
Loading 0:  50%|█████     | 183/363 [00:05<00:04, 37.79it/s]
Loading 0:  52%|█████▏    | 187/363 [00:05<00:04, 35.71it/s]
Loading 0:  53%|█████▎    | 192/363 [00:05<00:04, 38.10it/s]
Loading 0:  54%|█████▍    | 196/363 [00:06<00:04, 35.66it/s]
Loading 0:  55%|█████▌    | 201/363 [00:06<00:04, 37.54it/s]
Loading 0:  56%|█████▋    | 205/363 [00:06<00:04, 34.93it/s]
Loading 0:  58%|█████▊    | 209/363 [00:06<00:04, 35.74it/s]
Loading 0:  59%|█████▊    | 213/363 [00:06<00:04, 30.02it/s]
Loading 0:  60%|█████▉    | 217/363 [00:06<00:04, 30.35it/s]
Loading 0:  61%|██████    | 222/363 [00:06<00:04, 32.41it/s]
Loading 0:  62%|██████▏   | 226/363 [00:07<00:06, 20.72it/s]
Loading 0:  63%|██████▎   | 230/363 [00:07<00:06, 21.30it/s]
Loading 0:  65%|██████▍   | 235/363 [00:07<00:04, 25.80it/s]
Loading 0:  66%|██████▌   | 239/363 [00:07<00:05, 24.43it/s]
Loading 0:  67%|██████▋   | 244/363 [00:07<00:04, 28.52it/s]
Loading 0:  68%|██████▊   | 248/363 [00:08<00:04, 27.29it/s]
Loading 0:  70%|██████▉   | 253/363 [00:08<00:03, 31.44it/s]
Loading 0:  71%|███████   | 257/363 [00:08<00:03, 29.05it/s]
Loading 0:  72%|███████▏  | 262/363 [00:08<00:03, 33.58it/s]
Loading 0:  73%|███████▎  | 266/363 [00:08<00:03, 30.44it/s]
Loading 0:  75%|███████▍  | 271/363 [00:08<00:02, 33.67it/s]
Loading 0:  76%|███████▌  | 275/363 [00:08<00:02, 29.94it/s]
Loading 0:  77%|███████▋  | 280/363 [00:08<00:02, 33.74it/s]
Loading 0:  78%|███████▊  | 284/363 [00:09<00:02, 30.17it/s]
Loading 0:  80%|███████▉  | 289/363 [00:09<00:02, 33.64it/s]
Loading 0:  81%|████████  | 293/363 [00:09<00:02, 30.76it/s]
Loading 0:  82%|████████▏ | 298/363 [00:09<00:01, 34.25it/s]
Loading 0:  83%|████████▎ | 303/363 [00:09<00:01, 34.79it/s]
Loading 0:  85%|████████▍ | 307/363 [00:16<00:28,  1.97it/s]
Loading 0:  86%|████████▌ | 312/363 [00:17<00:18,  2.83it/s]
Loading 0:  88%|████████▊ | 319/363 [00:17<00:09,  4.51it/s]
Loading 0:  89%|████████▉ | 323/363 [00:17<00:07,  5.70it/s]
Loading 0:  90%|█████████ | 328/363 [00:17<00:04,  7.77it/s]
Loading 0:  92%|█████████▏| 333/363 [00:17<00:02, 10.38it/s]
Loading 0:  93%|█████████▎| 338/363 [00:17<00:01, 13.60it/s]
Loading 0:  95%|█████████▍| 344/363 [00:17<00:01, 17.54it/s]
Loading 0:  96%|█████████▌| 349/363 [00:17<00:00, 21.17it/s]
Loading 0:  98%|█████████▊| 356/363 [00:18<00:00, 27.71it/s]
Loading 0: 100%|█████████▉| 362/363 [00:18<00:00, 30.64it/s]
                                                            
Job chaiml-lexical-viral-v5a-2693-v4-mkmlizer completed after 114.32s with status: succeeded
Stopping job with name chaiml-lexical-viral-v5a-2693-v4-mkmlizer
Pipeline stage MKMLizer completed in 114.88s
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-lexical-viral-v5a-2693-v4
Waiting for inference service chaiml-lexical-viral-v5a-2693-v4 to be ready
Inference service chaiml-lexical-viral-v5a-2693-v4 ready after 180.9502546787262s
Pipeline stage MKMLDeployer completed in 181.63s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8467581272125244s
Received healthy response to inference request in 1.5056118965148926s
Received healthy response to inference request in 1.4999268054962158s
Received healthy response to inference request in 1.8502476215362549s
Received healthy response to inference request in 1.4107532501220703s
5 requests
0 failed requests
5th percentile: 1.4285879611968995
10th percentile: 1.4464226722717286
20th percentile: 1.4820920944213867
30th percentile: 1.5010638236999512
40th percentile: 1.5033378601074219
50th percentile: 1.5056118965148926
60th percentile: 1.6420703887939454
70th percentile: 1.778528881072998
80th percentile: 1.8474560260772706
90th percentile: 1.8488518238067626
95th percentile: 1.8495497226715087
99th percentile: 1.8501080417633056
mean time: 1.6226595401763917
Pipeline stage StressChecker completed in 9.43s
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 2.58s
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 2.05s
Shutdown handler de-registered
chaiml-lexical-viral-v5a_2693_v4 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 2558.52s
Shutdown handler de-registered
chaiml-lexical-viral-v5a_2693_v4 status is now inactive due to auto deactivation removed underperforming models
chaiml-lexical-viral-v5a_2693_v4 status is now torndown due to DeploymentManager action
chaiml-lexical-viral-v5a_2693_v4 status is now torndown due to DeploymentManager action
chaiml-lexical-viral-v5a_2693_v4 status is now torndown due to DeploymentManager action