developer_uid: Hastagaras
submission_id: hastagaras-lm3-1-stage-five_v1
model_name: test
model_group: Hastagaras/LM3.1-STAGE-F
status: torndown
timestamp: 2024-11-11T20:20:57+00:00
num_battles: 20213
num_wins: 9439
celo_rating: 1219.37
family_friendly_score: 0.5736
family_friendly_standard_error: 0.006994040892073766
submission_type: basic
model_repo: Hastagaras/LM3.1-STAGE-FIVE
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.8555799539658117, 'latency_mean': 1.1687401747703552, 'latency_p50': 1.1785998344421387, 'latency_p90': 1.2923635721206665}, {'batch_size': 4, 'throughput': 1.8028583360420456, 'latency_mean': 2.2109420931339265, 'latency_p50': 2.203933000564575, 'latency_p90': 2.427947521209717}, {'batch_size': 5, 'throughput': 1.9386540071597613, 'latency_mean': 2.566214876174927, 'latency_p50': 2.568032145500183, 'latency_p90': 2.8777589559555055}, {'batch_size': 8, 'throughput': 2.1602737905821625, 'latency_mean': 3.6801064717769623, 'latency_p50': 3.7000426054000854, 'latency_p90': 4.122227001190185}, {'batch_size': 10, 'throughput': 2.215334262091825, 'latency_mean': 4.472725780010223, 'latency_p50': 4.493578195571899, 'latency_p90': 5.090043210983277}, {'batch_size': 12, 'throughput': 2.238428811582117, 'latency_mean': 5.311550004482269, 'latency_p50': 5.33582866191864, 'latency_p90': 6.0135674476623535}, {'batch_size': 15, 'throughput': 2.2464266703523816, 'latency_mean': 6.594242187738419, 'latency_p50': 6.656296968460083, 'latency_p90': 7.3369886636734005}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: test
is_internal_developer: False
language_model: Hastagaras/LM3.1-STAGE-FIVE
model_size: 8B
ranking_group: single
throughput_3p7s: 2.18
us_pacific_date: 2024-11-11
win_ratio: 0.46697669816454757
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 60, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}\n[start]<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{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 hastagaras-lm3-1-stage-five-v1-mkmlizer
Waiting for job on hastagaras-lm3-1-stage-five-v1-mkmlizer to finish
hastagaras-lm3-1-stage-five-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-lm3-1-stage-five-v1-mkmlizer: ║     _____            __           __                                ║
hastagaras-lm3-1-stage-five-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-lm3-1-stage-five-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-lm3-1-stage-five-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-lm3-1-stage-five-v1-mkmlizer: ║       /___/                                                         ║
hastagaras-lm3-1-stage-five-v1-mkmlizer: ║                                                                     ║
hastagaras-lm3-1-stage-five-v1-mkmlizer: ║  Version: 0.11.33                                                   ║
hastagaras-lm3-1-stage-five-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-lm3-1-stage-five-v1-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-lm3-1-stage-five-v1-mkmlizer: ║                                                                     ║
hastagaras-lm3-1-stage-five-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-lm3-1-stage-five-v1-mkmlizer: ║  belonging to:                                                      ║
hastagaras-lm3-1-stage-five-v1-mkmlizer: ║                                                                     ║
hastagaras-lm3-1-stage-five-v1-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-lm3-1-stage-five-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-lm3-1-stage-five-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
hastagaras-lm3-1-stage-five-v1-mkmlizer: ║                                                                     ║
hastagaras-lm3-1-stage-five-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
hastagaras-lm3-1-stage-five-v1-mkmlizer: Downloaded to shared memory in 80.304s
hastagaras-lm3-1-stage-five-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp87_rb2oy, device:0
hastagaras-lm3-1-stage-five-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
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
hastagaras-lm3-1-stage-five-v1-mkmlizer: quantized model in 26.894s
hastagaras-lm3-1-stage-five-v1-mkmlizer: Processed model Hastagaras/LM3.1-STAGE-FIVE in 107.199s
hastagaras-lm3-1-stage-five-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-lm3-1-stage-five-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-lm3-1-stage-five-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-lm3-1-stage-five-v1
hastagaras-lm3-1-stage-five-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-lm3-1-stage-five-v1/config.json
hastagaras-lm3-1-stage-five-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-lm3-1-stage-five-v1/special_tokens_map.json
hastagaras-lm3-1-stage-five-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-lm3-1-stage-five-v1/tokenizer_config.json
hastagaras-lm3-1-stage-five-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-lm3-1-stage-five-v1/tokenizer.json
hastagaras-lm3-1-stage-five-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-lm3-1-stage-five-v1/flywheel_model.0.safetensors
hastagaras-lm3-1-stage-five-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:08, 32.08it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:05, 52.49it/s]
Loading 0:   7%|▋         | 19/291 [00:00<00:05, 45.37it/s]
Loading 0:   8%|▊         | 24/291 [00:00<00:06, 43.85it/s]
Loading 0:  10%|█         | 30/291 [00:00<00:05, 48.60it/s]
Loading 0:  12%|█▏        | 36/291 [00:00<00:05, 48.76it/s]
Loading 0:  14%|█▍        | 42/291 [00:00<00:06, 40.14it/s]
Loading 0:  17%|█▋        | 49/291 [00:01<00:05, 46.54it/s]
Loading 0:  19%|█▉        | 55/291 [00:01<00:05, 45.75it/s]
Loading 0:  21%|██        | 60/291 [00:01<00:05, 43.37it/s]
Loading 0:  23%|██▎       | 66/291 [00:01<00:04, 47.10it/s]
Loading 0:  24%|██▍       | 71/291 [00:01<00:04, 46.48it/s]
Loading 0:  26%|██▌       | 76/291 [00:01<00:04, 47.17it/s]
Loading 0:  28%|██▊       | 82/291 [00:01<00:04, 45.91it/s]
Loading 0:  30%|██▉       | 87/291 [00:02<00:07, 28.52it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:05, 35.56it/s]
Loading 0:  34%|███▍      | 100/291 [00:02<00:05, 37.59it/s]
Loading 0:  36%|███▌      | 105/291 [00:02<00:04, 39.11it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:04, 44.57it/s]
Loading 0:  40%|████      | 117/291 [00:02<00:03, 45.05it/s]
Loading 0:  42%|████▏     | 122/291 [00:02<00:04, 39.77it/s]
Loading 0:  45%|████▍     | 130/291 [00:03<00:03, 48.47it/s]
Loading 0:  47%|████▋     | 136/291 [00:03<00:03, 47.34it/s]
Loading 0:  49%|████▉     | 142/291 [00:03<00:03, 46.84it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:02, 49.24it/s]
Loading 0:  53%|█████▎    | 154/291 [00:03<00:02, 46.62it/s]
Loading 0:  55%|█████▍    | 159/291 [00:03<00:02, 46.69it/s]
Loading 0:  57%|█████▋    | 166/291 [00:03<00:02, 50.93it/s]
Loading 0:  59%|█████▉    | 172/291 [00:03<00:02, 48.64it/s]
Loading 0:  61%|██████    | 177/291 [00:03<00:02, 48.00it/s]
Loading 0:  63%|██████▎   | 182/291 [00:04<00:02, 47.00it/s]
Loading 0:  64%|██████▍   | 187/291 [00:04<00:03, 31.26it/s]
Loading 0:  66%|██████▌   | 191/291 [00:04<00:03, 32.81it/s]
Loading 0:  67%|██████▋   | 195/291 [00:04<00:02, 33.70it/s]
Loading 0:  69%|██████▉   | 202/291 [00:04<00:02, 41.58it/s]
Loading 0:  71%|███████▏  | 208/291 [00:04<00:01, 42.24it/s]
Loading 0:  73%|███████▎  | 213/291 [00:04<00:01, 40.80it/s]
Loading 0:  75%|███████▌  | 219/291 [00:05<00:01, 45.34it/s]
Loading 0:  77%|███████▋  | 225/291 [00:05<00:01, 48.76it/s]
Loading 0:  79%|███████▉  | 231/291 [00:05<00:01, 44.72it/s]
Loading 0:  82%|████████▏ | 238/291 [00:05<00:01, 50.24it/s]
Loading 0:  84%|████████▍ | 244/291 [00:05<00:00, 48.49it/s]
Loading 0:  86%|████████▌ | 250/291 [00:05<00:00, 49.17it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 49.23it/s]
Loading 0:  90%|█████████ | 262/291 [00:05<00:00, 44.55it/s]
Loading 0:  92%|█████████▏| 267/291 [00:06<00:00, 42.19it/s]
Loading 0:  94%|█████████▍| 273/291 [00:06<00:00, 44.79it/s]
Loading 0:  96%|█████████▌| 278/291 [00:06<00:00, 43.80it/s]
Loading 0:  97%|█████████▋| 283/291 [00:06<00:00, 40.24it/s]
Loading 0:  99%|█████████▉| 288/291 [00:12<00:00,  3.02it/s]
                                                            

Job hastagaras-lm3-1-stage-five-v1-mkmlizer completed after 136.11s with status: succeeded
Stopping job with name hastagaras-lm3-1-stage-five-v1-mkmlizer
Pipeline stage MKMLizer completed in 136.67s
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 hastagaras-lm3-1-stage-five-v1
Waiting for inference service hastagaras-lm3-1-stage-five-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
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 hastagaras-lm3-1-stage-five-v1 ready after 180.76631426811218s
Pipeline stage MKMLDeployer completed in 181.44s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9189798831939697s
Received healthy response to inference request in 1.7197248935699463s
Received healthy response to inference request in 1.4546339511871338s
Received healthy response to inference request in 1.3584985733032227s
Received healthy response to inference request in 1.2690470218658447s
5 requests
0 failed requests
5th percentile: 1.2869373321533204
10th percentile: 1.3048276424407959
20th percentile: 1.340608263015747
30th percentile: 1.377725648880005
40th percentile: 1.4161798000335692
50th percentile: 1.4546339511871338
60th percentile: 1.5606703281402587
70th percentile: 1.6667067050933837
80th percentile: 1.759575891494751
90th percentile: 1.8392778873443603
95th percentile: 1.879128885269165
99th percentile: 1.9110096836090087
mean time: 1.5441768646240235
Pipeline stage StressChecker completed in 9.41s
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 2.50s
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 2.41s
Shutdown handler de-registered
hastagaras-lm3-1-stage-five_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 2626.96s
Shutdown handler de-registered
hastagaras-lm3-1-stage-five_v1 status is now inactive due to auto deactivation removed underperforming models
hastagaras-lm3-1-stage-five_v1 status is now torndown due to DeploymentManager action