chaiml-elo-alignment-run-3

developer_uid: zonemercy

submission_id: chaiml-elo-alignment-run-3_v60

model_name: chaiml-elo-alignment-run-3_v60

model_group: ChaiML/elo_alignment_run

status: inactive

timestamp: 2024-12-03T10:28:05+00:00

num_battles: 10862

num_wins: 5504

celo_rating: 1267.16

family_friendly_score: 0.5846

family_friendly_standard_error: 0.006969115295358515

submission_type: basic

model_repo: ChaiML/elo_alignment_run_3

model_architecture: LlamaForCausalLM

model_num_parameters: 8030261248.0

best_of: 16

max_input_tokens: 512

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.9076729966101931, 'latency_mean': 1.1016524505615235, 'latency_p50': 1.1017597913742065, 'latency_p90': 1.2270014047622682}, {'batch_size': 4, 'throughput': 1.7985566694046928, 'latency_mean': 2.2151149952411653, 'latency_p50': 2.2131770849227905, 'latency_p90': 2.4973782539367675}, {'batch_size': 5, 'throughput': 1.8912462692753356, 'latency_mean': 2.6275482678413393, 'latency_p50': 2.6138728857040405, 'latency_p90': 2.947708177566528}, {'batch_size': 8, 'throughput': 1.9827324087596632, 'latency_mean': 4.003761311769486, 'latency_p50': 4.0395050048828125, 'latency_p90': 4.464961504936218}, {'batch_size': 10, 'throughput': 2.0624963380927044, 'latency_mean': 4.800083522796631, 'latency_p50': 4.817941784858704, 'latency_p90': 5.470369601249695}, {'batch_size': 12, 'throughput': 2.070290099820781, 'latency_mean': 5.723951333761216, 'latency_p50': 5.830292582511902, 'latency_p90': 6.471145796775818}, {'batch_size': 15, 'throughput': 2.0419999600100813, 'latency_mean': 7.211336823701859, 'latency_p50': 7.284807205200195, 'latency_p90': 8.18151261806488}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-elo-alignment-run-3_v60

is_internal_developer: True

language_model: ChaiML/elo_alignment_run_3

model_size: 8B

ranking_group: single

throughput_3p7s: 1.98

us_pacific_date: 2024-12-03

win_ratio: 0.5067206775916038

generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}

formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', '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-elo-alignment-run-3-v60-mkmlizer
Waiting for job on chaiml-elo-alignment-run-3-v60-mkmlizer to finish
chaiml-elo-alignment-run-3-v60-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-elo-alignment-run-3-v60-mkmlizer: ║     _____            __           __                                ║
chaiml-elo-alignment-run-3-v60-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-elo-alignment-run-3-v60-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-elo-alignment-run-3-v60-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-elo-alignment-run-3-v60-mkmlizer: ║       /___/                                                         ║
chaiml-elo-alignment-run-3-v60-mkmlizer: ║                                                                     ║
chaiml-elo-alignment-run-3-v60-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-elo-alignment-run-3-v60-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-elo-alignment-run-3-v60-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-elo-alignment-run-3-v60-mkmlizer: ║                                                                     ║
chaiml-elo-alignment-run-3-v60-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-elo-alignment-run-3-v60-mkmlizer: ║  belonging to:                                                      ║
chaiml-elo-alignment-run-3-v60-mkmlizer: ║                                                                     ║
chaiml-elo-alignment-run-3-v60-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-elo-alignment-run-3-v60-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-elo-alignment-run-3-v60-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-elo-alignment-run-3-v60-mkmlizer: ║                                                                     ║
chaiml-elo-alignment-run-3-v60-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-elo-alignment-run-3-v60-mkmlizer: Downloaded to shared memory in 61.760s
chaiml-elo-alignment-run-3-v60-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpciy6rs9h, device:0
chaiml-elo-alignment-run-3-v60-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-elo-alignment-run-3-v60-mkmlizer: quantized model in 31.963s
chaiml-elo-alignment-run-3-v60-mkmlizer: Processed model ChaiML/elo_alignment_run_3 in 93.723s
chaiml-elo-alignment-run-3-v60-mkmlizer: creating bucket guanaco-mkml-models
chaiml-elo-alignment-run-3-v60-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-elo-alignment-run-3-v60-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v60
chaiml-elo-alignment-run-3-v60-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v60/config.json
chaiml-elo-alignment-run-3-v60-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v60/special_tokens_map.json
chaiml-elo-alignment-run-3-v60-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v60/tokenizer_config.json
chaiml-elo-alignment-run-3-v60-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v60/tokenizer.json
chaiml-elo-alignment-run-3-v60-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v60/flywheel_model.0.safetensors
chaiml-elo-alignment-run-3-v60-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:13, 21.96it/s]
Loading 0:   3%|▎         | 10/291 [00:00<00:09, 31.15it/s]
Loading 0:   5%|▍         | 14/291 [00:00<00:12, 22.58it/s]
Loading 0:   7%|▋         | 19/291 [00:00<00:09, 27.85it/s]
Loading 0:   8%|▊         | 23/291 [00:00<00:11, 23.60it/s]
Loading 0:  10%|▉         | 28/291 [00:01<00:09, 28.03it/s]
Loading 0:  11%|█         | 32/291 [00:01<00:08, 29.32it/s]
Loading 0:  12%|█▏        | 36/291 [00:01<00:14, 18.04it/s]
Loading 0:  14%|█▍        | 41/291 [00:01<00:12, 20.11it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:09, 26.93it/s]
Loading 0:  18%|█▊        | 52/291 [00:02<00:08, 26.70it/s]
Loading 0:  20%|█▉        | 57/291 [00:02<00:07, 29.74it/s]
Loading 0:  21%|██        | 61/291 [00:02<00:07, 29.19it/s]
Loading 0:  23%|██▎       | 66/291 [00:02<00:07, 31.87it/s]
Loading 0:  24%|██▍       | 70/291 [00:02<00:07, 30.81it/s]
Loading 0:  25%|██▌       | 74/291 [00:02<00:06, 31.26it/s]
Loading 0:  27%|██▋       | 78/291 [00:02<00:06, 31.50it/s]
Loading 0:  28%|██▊       | 82/291 [00:03<00:09, 21.46it/s]
Loading 0:  29%|██▉       | 85/291 [00:03<00:09, 22.42it/s]
Loading 0:  31%|███       | 90/291 [00:03<00:07, 26.52it/s]
Loading 0:  32%|███▏      | 94/291 [00:03<00:07, 26.48it/s]
Loading 0:  33%|███▎      | 97/291 [00:03<00:07, 26.76it/s]
Loading 0:  35%|███▍      | 101/291 [00:03<00:07, 24.19it/s]
Loading 0:  36%|███▋      | 106/291 [00:04<00:06, 29.41it/s]
Loading 0:  38%|███▊      | 110/291 [00:04<00:07, 25.72it/s]
Loading 0:  40%|███▉      | 115/291 [00:04<00:05, 29.59it/s]
Loading 0:  41%|████      | 120/291 [00:04<00:05, 30.06it/s]
Loading 0:  43%|████▎     | 126/291 [00:04<00:04, 34.39it/s]
Loading 0:  45%|████▍     | 130/291 [00:04<00:04, 32.65it/s]
Loading 0:  46%|████▌     | 134/291 [00:05<00:07, 21.88it/s]
Loading 0:  47%|████▋     | 137/291 [00:05<00:06, 22.38it/s]
Loading 0:  48%|████▊     | 140/291 [00:05<00:07, 19.56it/s]
Loading 0:  50%|████▉     | 145/291 [00:05<00:05, 24.45it/s]
Loading 0:  51%|█████     | 149/291 [00:05<00:06, 22.67it/s]
Loading 0:  53%|█████▎    | 154/291 [00:05<00:05, 26.94it/s]
Loading 0:  54%|█████▍    | 158/291 [00:06<00:05, 23.61it/s]
Loading 0:  56%|█████▌    | 163/291 [00:06<00:04, 27.99it/s]
Loading 0:  57%|█████▋    | 167/291 [00:06<00:05, 24.52it/s]
Loading 0:  59%|█████▉    | 172/291 [00:06<00:04, 28.28it/s]
Loading 0:  60%|██████    | 176/291 [00:06<00:04, 24.84it/s]
Loading 0:  62%|██████▏   | 181/291 [00:06<00:03, 28.61it/s]
Loading 0:  64%|██████▎   | 185/291 [00:07<00:03, 29.52it/s]
Loading 0:  65%|██████▍   | 189/291 [00:07<00:05, 18.94it/s]
Loading 0:  67%|██████▋   | 194/291 [00:07<00:04, 20.72it/s]
Loading 0:  68%|██████▊   | 199/291 [00:07<00:03, 25.11it/s]
Loading 0:  70%|██████▉   | 203/291 [00:07<00:03, 23.77it/s]
Loading 0:  71%|███████▏  | 208/291 [00:08<00:02, 28.02it/s]
Loading 0:  73%|███████▎  | 212/291 [00:08<00:03, 25.49it/s]
Loading 0:  75%|███████▍  | 217/291 [00:08<00:02, 29.50it/s]
Loading 0:  76%|███████▌  | 221/291 [00:08<00:02, 25.71it/s]
Loading 0:  78%|███████▊  | 226/291 [00:08<00:02, 29.64it/s]
Loading 0:  79%|███████▉  | 230/291 [00:08<00:02, 27.37it/s]
Loading 0:  80%|████████  | 234/291 [00:09<00:02, 20.46it/s]
Loading 0:  82%|████████▏ | 239/291 [00:09<00:02, 20.67it/s]
Loading 0:  84%|████████▍ | 244/291 [00:09<00:01, 24.40it/s]
Loading 0:  85%|████████▌ | 248/291 [00:09<00:01, 22.78it/s]
Loading 0:  87%|████████▋ | 253/291 [00:09<00:01, 26.52it/s]
Loading 0:  88%|████████▊ | 257/291 [00:10<00:01, 23.82it/s]
Loading 0:  90%|█████████ | 262/291 [00:10<00:01, 27.85it/s]
Loading 0:  91%|█████████▏| 266/291 [00:10<00:00, 25.38it/s]
Loading 0:  93%|█████████▎| 271/291 [00:10<00:00, 30.11it/s]
Loading 0:  95%|█████████▍| 275/291 [00:10<00:00, 27.22it/s]
Loading 0:  97%|█████████▋| 281/291 [00:10<00:00, 31.93it/s]
Loading 0:  98%|█████████▊| 286/291 [00:16<00:01,  2.66it/s]
Loading 0:  99%|█████████▉| 289/291 [00:16<00:00,  3.25it/s]
                                                            
Job chaiml-elo-alignment-run-3-v60-mkmlizer completed after 137.7s with status: succeeded
Stopping job with name chaiml-elo-alignment-run-3-v60-mkmlizer
Pipeline stage MKMLizer completed in 138.22s
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 chaiml-elo-alignment-run-3-v60
Waiting for inference service chaiml-elo-alignment-run-3-v60 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
Inference service chaiml-elo-alignment-run-3-v60 ready after 150.54822039604187s
Pipeline stage MKMLDeployer completed in 151.08s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.199108362197876s
Received healthy response to inference request in 1.408595323562622s
Received healthy response to inference request in 1.508211612701416s
Received healthy response to inference request in 1.4029276371002197s
Received healthy response to inference request in 1.34647536277771s
5 requests
0 failed requests
5th percentile: 1.3577658176422118
10th percentile: 1.369056272506714
20th percentile: 1.3916371822357179
30th percentile: 1.4040611743927003
40th percentile: 1.4063282489776612
50th percentile: 1.408595323562622
60th percentile: 1.4484418392181397
70th percentile: 1.4882883548736572
80th percentile: 1.646390962600708
90th percentile: 1.9227496623992921
95th percentile: 2.0609290122985837
99th percentile: 2.1714724922180175
mean time: 1.5730636596679688
Pipeline stage StressChecker completed in 9.16s
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 2.52s
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 2.52s
Shutdown handler de-registered
chaiml-elo-alignment-run-3_v60 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 2852.86s
Shutdown handler de-registered
chaiml-elo-alignment-run-3_v60 status is now inactive due to auto deactivation removed underperforming models