submission_id: chaiml-sao10k-l3-rp-v3-3_v94
developer_uid: chai_backend_admin
best_of: 8
celo_rating: 1250.33
display_name: chaiml-sao10k-l3-rp-v3-3_v94
family_friendly_score: 0.5668
family_friendly_standard_error: 0.007007678074797671
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}<|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}
generation_params: {'temperature': 0.95, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|end_header_id|>,', '<|eot_id|>,', '\n\n{user_name}'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: True
language_model: ChaiML/sao10k-l3-rp-v3-3
latencies: [{'batch_size': 1, 'throughput': 0.8435795376081551, 'latency_mean': 1.1853207743167877, 'latency_p50': 1.1893970966339111, 'latency_p90': 1.3055377006530762}, {'batch_size': 4, 'throughput': 1.783342074505948, 'latency_mean': 2.2425689911842346, 'latency_p50': 2.2570847272872925, 'latency_p90': 2.491593313217163}, {'batch_size': 5, 'throughput': 1.8995674085022927, 'latency_mean': 2.6198256397247315, 'latency_p50': 2.627868175506592, 'latency_p90': 2.9085527420043946}, {'batch_size': 8, 'throughput': 2.117287285635594, 'latency_mean': 3.7516335356235504, 'latency_p50': 3.7435232400894165, 'latency_p90': 4.187487030029297}, {'batch_size': 10, 'throughput': 2.1376970805955016, 'latency_mean': 4.640988818407059, 'latency_p50': 4.651956558227539, 'latency_p90': 5.153514099121094}, {'batch_size': 12, 'throughput': 2.1961493218530834, 'latency_mean': 5.4077134346961975, 'latency_p50': 5.435555338859558, 'latency_p90': 6.100770115852356}, {'batch_size': 15, 'throughput': 2.1796979345751266, 'latency_mean': 6.785671211481095, 'latency_p50': 6.73848032951355, 'latency_p90': 7.5741633653640745}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: ChaiML/sao10k-l3-rp-v3-3
model_name: chaiml-sao10k-l3-rp-v3-3_v94
model_num_parameters: 8030261248.0
model_repo: ChaiML/sao10k-l3-rp-v3-3
model_size: 8B
num_battles: 12030
num_wins: 6265
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 2.13
timestamp: 2024-11-11T18:00:46+00:00
us_pacific_date: 2024-11-11
win_ratio: 0.5207813798836243
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-sao10k-l3-rp-v3-3-v94-mkmlizer
Waiting for job on chaiml-sao10k-l3-rp-v3-3-v94-mkmlizer to finish
chaiml-sao10k-l3-rp-v3-3-v94-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-sao10k-l3-rp-v3-3-v94-mkmlizer: ║     _____            __           __                                ║
chaiml-sao10k-l3-rp-v3-3-v94-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-sao10k-l3-rp-v3-3-v94-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-sao10k-l3-rp-v3-3-v94-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-sao10k-l3-rp-v3-3-v94-mkmlizer: ║       /___/                                                         ║
chaiml-sao10k-l3-rp-v3-3-v94-mkmlizer: ║                                                                     ║
chaiml-sao10k-l3-rp-v3-3-v94-mkmlizer: ║  Version: 0.11.33                                                   ║
chaiml-sao10k-l3-rp-v3-3-v94-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-sao10k-l3-rp-v3-3-v94-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-sao10k-l3-rp-v3-3-v94-mkmlizer: ║                                                                     ║
chaiml-sao10k-l3-rp-v3-3-v94-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-sao10k-l3-rp-v3-3-v94-mkmlizer: ║  belonging to:                                                      ║
chaiml-sao10k-l3-rp-v3-3-v94-mkmlizer: ║                                                                     ║
chaiml-sao10k-l3-rp-v3-3-v94-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-sao10k-l3-rp-v3-3-v94-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-sao10k-l3-rp-v3-3-v94-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-sao10k-l3-rp-v3-3-v94-mkmlizer: ║                                                                     ║
chaiml-sao10k-l3-rp-v3-3-v94-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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-sao10k-l3-rp-v3-3-v94-mkmlizer: Downloaded to shared memory in 134.622s
chaiml-sao10k-l3-rp-v3-3-v94-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpiyk1y9pt, device:0
chaiml-sao10k-l3-rp-v3-3-v94-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-sao10k-l3-rp-v3-3-v94-mkmlizer: quantized model in 26.957s
chaiml-sao10k-l3-rp-v3-3-v94-mkmlizer: Processed model ChaiML/sao10k-l3-rp-v3-3 in 161.580s
chaiml-sao10k-l3-rp-v3-3-v94-mkmlizer: creating bucket guanaco-mkml-models
chaiml-sao10k-l3-rp-v3-3-v94-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-sao10k-l3-rp-v3-3-v94-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v94
chaiml-sao10k-l3-rp-v3-3-v94-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v94/config.json
chaiml-sao10k-l3-rp-v3-3-v94-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v94/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v94-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v94/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v94-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v94/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v94-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v94/flywheel_model.0.safetensors
chaiml-sao10k-l3-rp-v3-3-v94-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<11:38,  2.42s/it]
Loading 0:   2%|▏         | 6/291 [00:05<03:07,  1.52it/s]
Loading 0:   4%|▍         | 11/291 [00:05<01:22,  3.38it/s]
Loading 0:   5%|▌         | 15/291 [00:05<00:53,  5.19it/s]
Loading 0:   8%|▊         | 22/291 [00:05<00:28,  9.50it/s]
Loading 0:   9%|▉         | 26/291 [00:05<00:22, 11.97it/s]
Loading 0:  11%|█         | 31/291 [00:05<00:16, 15.93it/s]
Loading 0:  12%|█▏        | 36/291 [00:05<00:12, 19.87it/s]
Loading 0:  14%|█▍        | 41/291 [00:05<00:10, 23.83it/s]
Loading 0:  16%|█▌        | 46/291 [00:05<00:08, 27.88it/s]
Loading 0:  18%|█▊        | 51/291 [00:06<00:08, 27.22it/s]
Loading 0:  20%|██        | 59/291 [00:06<00:06, 36.67it/s]
Loading 0:  22%|██▏       | 64/291 [00:06<00:08, 28.33it/s]
Loading 0:  24%|██▎       | 69/291 [00:06<00:07, 29.19it/s]
Loading 0:  26%|██▋       | 77/291 [00:06<00:05, 38.00it/s]
Loading 0:  29%|██▊       | 83/291 [00:06<00:05, 39.19it/s]
Loading 0:  30%|███       | 88/291 [00:07<00:05, 40.23it/s]
Loading 0:  32%|███▏      | 94/291 [00:07<00:04, 44.70it/s]
Loading 0:  34%|███▍      | 100/291 [00:07<00:03, 48.05it/s]
Loading 0:  36%|███▋      | 106/291 [00:07<00:04, 43.55it/s]
Loading 0:  39%|███▉      | 113/291 [00:07<00:03, 49.33it/s]
Loading 0:  41%|████      | 119/291 [00:07<00:03, 48.08it/s]
Loading 0:  43%|████▎     | 125/291 [00:07<00:03, 50.22it/s]
Loading 0:  45%|████▌     | 132/291 [00:07<00:03, 46.32it/s]
Loading 0:  48%|████▊     | 139/291 [00:08<00:03, 50.45it/s]
Loading 0:  50%|████▉     | 145/291 [00:08<00:02, 50.07it/s]
Loading 0:  52%|█████▏    | 151/291 [00:08<00:03, 43.52it/s]
Loading 0:  54%|█████▍    | 158/291 [00:08<00:02, 48.54it/s]
Loading 0:  56%|█████▋    | 164/291 [00:08<00:02, 45.82it/s]
Loading 0:  58%|█████▊    | 169/291 [00:08<00:03, 32.03it/s]
Loading 0:  60%|██████    | 176/291 [00:09<00:03, 38.13it/s]
Loading 0:  63%|██████▎   | 182/291 [00:09<00:02, 38.68it/s]
Loading 0:  64%|██████▍   | 187/291 [00:09<00:02, 39.81it/s]
Loading 0:  67%|██████▋   | 194/291 [00:09<00:02, 45.51it/s]
Loading 0:  69%|██████▊   | 200/291 [00:09<00:02, 43.89it/s]
Loading 0:  70%|███████   | 205/291 [00:09<00:01, 44.13it/s]
Loading 0:  73%|███████▎  | 212/291 [00:09<00:01, 49.52it/s]
Loading 0:  75%|███████▍  | 218/291 [00:09<00:01, 44.61it/s]
Loading 0:  77%|███████▋  | 223/291 [00:10<00:01, 43.98it/s]
Loading 0:  79%|███████▉  | 230/291 [00:10<00:01, 48.92it/s]
Loading 0:  81%|████████  | 236/291 [00:10<00:01, 45.30it/s]
Loading 0:  83%|████████▎ | 241/291 [00:10<00:01, 44.11it/s]
Loading 0:  85%|████████▌ | 248/291 [00:10<00:00, 49.45it/s]
Loading 0:  87%|████████▋ | 254/291 [00:10<00:00, 46.31it/s]
Loading 0:  89%|████████▉ | 259/291 [00:10<00:00, 43.85it/s]
Loading 0:  91%|█████████ | 265/291 [00:10<00:00, 47.13it/s]
Loading 0:  93%|█████████▎| 270/291 [00:11<00:00, 30.82it/s]
Loading 0:  94%|█████████▍| 274/291 [00:11<00:00, 32.23it/s]
Loading 0:  96%|█████████▌| 278/291 [00:11<00:00, 32.72it/s]
Loading 0:  98%|█████████▊| 284/291 [00:11<00:00, 37.38it/s]
Loading 0:  99%|█████████▉| 289/291 [00:11<00:00, 40.22it/s]
                                                            

Job chaiml-sao10k-l3-rp-v3-3-v94-mkmlizer completed after 210.27s with status: succeeded
Stopping job with name chaiml-sao10k-l3-rp-v3-3-v94-mkmlizer
Pipeline stage MKMLizer completed in 210.79s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-sao10k-l3-rp-v3-3-v94
Waiting for inference service chaiml-sao10k-l3-rp-v3-3-v94 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
Inference service chaiml-sao10k-l3-rp-v3-3-v94 ready after 180.63375544548035s
Pipeline stage MKMLDeployer completed in 181.21s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9633448123931885s
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
Received healthy response to inference request in 1.8172998428344727s
Received healthy response to inference request in 1.20540452003479s
Received healthy response to inference request in 1.1650540828704834s
Received healthy response to inference request in 1.4188122749328613s
5 requests
0 failed requests
5th percentile: 1.1731241703033448
10th percentile: 1.181194257736206
20th percentile: 1.1973344326019286
30th percentile: 1.2480860710144044
40th percentile: 1.3334491729736329
50th percentile: 1.4188122749328613
60th percentile: 1.578207302093506
70th percentile: 1.7376023292541503
80th percentile: 1.846508836746216
90th percentile: 1.9049268245697022
95th percentile: 1.9341358184814452
99th percentile: 1.9575030136108398
mean time: 1.5139831066131593
Pipeline stage StressChecker completed in 9.45s
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 2.30s
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 2.18s
Shutdown handler de-registered
chaiml-sao10k-l3-rp-v3-3_v94 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 2464.83s
Shutdown handler de-registered
chaiml-sao10k-l3-rp-v3-3_v94 status is now inactive due to auto deactivation removed underperforming models