submission_id: chaiml-elo-alignment-run-3_v39
developer_uid: azuruce
alignment_samples: 12019
alignment_score: -1.221386895613878
best_of: 16
celo_rating: 1266.43
display_name: chaiml-elo-alignment-run-3_v3
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}
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}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: True
language_model: ChaiML/elo_alignment_run_3
latencies: [{'batch_size': 1, 'throughput': 0.9110416971112606, 'latency_mean': 1.097578340768814, 'latency_p50': 1.108667254447937, 'latency_p90': 1.21417293548584}, {'batch_size': 4, 'throughput': 1.8258017739791412, 'latency_mean': 2.1807720708847045, 'latency_p50': 2.180372714996338, 'latency_p90': 2.443341207504272}, {'batch_size': 5, 'throughput': 1.895082571752147, 'latency_mean': 2.615719587802887, 'latency_p50': 2.6418553590774536, 'latency_p90': 2.9230329275131224}, {'batch_size': 8, 'throughput': 2.035245243275675, 'latency_mean': 3.9055146408081054, 'latency_p50': 3.8845348358154297, 'latency_p90': 4.374354529380798}, {'batch_size': 10, 'throughput': 2.0557785420203887, 'latency_mean': 4.819998301267624, 'latency_p50': 4.8064268827438354, 'latency_p90': 5.536177849769592}, {'batch_size': 12, 'throughput': 2.0740723861896453, 'latency_mean': 5.702206553220749, 'latency_p50': 5.672398209571838, 'latency_p90': 6.585373973846435}, {'batch_size': 15, 'throughput': 2.036578518625041, 'latency_mean': 7.224648594856262, 'latency_p50': 7.3691874742507935, 'latency_p90': 8.010371589660645}]
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: ChaiML/elo_alignment_run
model_name: chaiml-elo-alignment-run-3_v3
model_num_parameters: 8030261248.0
model_repo: ChaiML/elo_alignment_run_3
model_size: 8B
num_battles: 12018
num_wins: 6502
propriety_score: 0.7366375121477162
propriety_total_count: 1029.0
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 2.03
timestamp: 2024-09-04T20:45:41+00:00
us_pacific_date: 2024-09-04
win_ratio: 0.5410218006323848
Download Preference Data
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-v39-mkmlizer
Waiting for job on chaiml-elo-alignment-run-3-v39-mkmlizer to finish
chaiml-elo-alignment-run-3-v39-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-elo-alignment-run-3-v39-mkmlizer: ║     _____            __           __                                ║
chaiml-elo-alignment-run-3-v39-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-elo-alignment-run-3-v39-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-elo-alignment-run-3-v39-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-elo-alignment-run-3-v39-mkmlizer: ║       /___/                                                         ║
chaiml-elo-alignment-run-3-v39-mkmlizer: ║                                                                     ║
chaiml-elo-alignment-run-3-v39-mkmlizer: ║  Version: 0.10.1                                                    ║
chaiml-elo-alignment-run-3-v39-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-elo-alignment-run-3-v39-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-elo-alignment-run-3-v39-mkmlizer: ║                                                                     ║
chaiml-elo-alignment-run-3-v39-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-elo-alignment-run-3-v39-mkmlizer: ║  belonging to:                                                      ║
chaiml-elo-alignment-run-3-v39-mkmlizer: ║                                                                     ║
chaiml-elo-alignment-run-3-v39-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-elo-alignment-run-3-v39-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-elo-alignment-run-3-v39-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-elo-alignment-run-3-v39-mkmlizer: ║                                                                     ║
chaiml-elo-alignment-run-3-v39-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-elo-alignment-run-3-v39-mkmlizer: Downloaded to shared memory in 52.796s
chaiml-elo-alignment-run-3-v39-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpd231wzey, device:0
chaiml-elo-alignment-run-3-v39-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-elo-alignment-run-3-v39-mkmlizer: quantized model in 28.738s
chaiml-elo-alignment-run-3-v39-mkmlizer: Processed model ChaiML/elo_alignment_run_3 in 81.534s
chaiml-elo-alignment-run-3-v39-mkmlizer: creating bucket guanaco-mkml-models
chaiml-elo-alignment-run-3-v39-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-elo-alignment-run-3-v39-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v39
chaiml-elo-alignment-run-3-v39-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v39/config.json
chaiml-elo-alignment-run-3-v39-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v39/special_tokens_map.json
chaiml-elo-alignment-run-3-v39-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v39/tokenizer_config.json
chaiml-elo-alignment-run-3-v39-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v39/tokenizer.json
chaiml-elo-alignment-run-3-v39-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v39/flywheel_model.0.safetensors
chaiml-elo-alignment-run-3-v39-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:10, 27.22it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:07, 37.61it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:08, 33.08it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:07, 36.15it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:08, 33.18it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:06, 38.51it/s]
Loading 0:  12%|█▏        | 36/291 [00:01<00:10, 24.17it/s]
Loading 0:  14%|█▍        | 41/291 [00:01<00:09, 25.79it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:07, 33.24it/s]
Loading 0:  18%|█▊        | 52/291 [00:01<00:07, 32.57it/s]
Loading 0:  20%|█▉        | 57/291 [00:01<00:06, 34.72it/s]
Loading 0:  21%|██        | 61/291 [00:01<00:06, 33.36it/s]
Loading 0:  23%|██▎       | 66/291 [00:01<00:06, 36.78it/s]
Loading 0:  24%|██▍       | 70/291 [00:02<00:06, 34.47it/s]
Loading 0:  25%|██▌       | 74/291 [00:02<00:06, 35.07it/s]
Loading 0:  27%|██▋       | 78/291 [00:02<00:06, 35.13it/s]
Loading 0:  28%|██▊       | 82/291 [00:02<00:08, 25.04it/s]
Loading 0:  29%|██▉       | 85/291 [00:02<00:08, 25.71it/s]
Loading 0:  31%|███       | 90/291 [00:02<00:06, 30.08it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:06, 29.80it/s]
Loading 0:  34%|███▍      | 99/291 [00:03<00:05, 34.12it/s]
Loading 0:  35%|███▌      | 103/291 [00:03<00:05, 32.87it/s]
Loading 0:  37%|███▋      | 108/291 [00:03<00:05, 34.43it/s]
Loading 0:  38%|███▊      | 112/291 [00:03<00:05, 32.69it/s]
Loading 0:  40%|███▉      | 116/291 [00:03<00:05, 34.02it/s]
Loading 0:  42%|████▏     | 122/291 [00:03<00:04, 39.04it/s]
Loading 0:  44%|████▎     | 127/291 [00:03<00:04, 36.29it/s]
Loading 0:  46%|████▌     | 133/291 [00:04<00:05, 30.10it/s]
Loading 0:  47%|████▋     | 137/291 [00:04<00:05, 30.43it/s]
Loading 0:  48%|████▊     | 141/291 [00:04<00:05, 27.78it/s]
Loading 0:  50%|████▉     | 145/291 [00:04<00:04, 30.11it/s]
Loading 0:  51%|█████     | 149/291 [00:04<00:05, 27.60it/s]
Loading 0:  53%|█████▎    | 154/291 [00:04<00:04, 32.03it/s]
Loading 0:  54%|█████▍    | 158/291 [00:05<00:04, 29.27it/s]
Loading 0:  57%|█████▋    | 165/291 [00:05<00:03, 36.55it/s]
Loading 0:  58%|█████▊    | 169/291 [00:05<00:03, 33.94it/s]
Loading 0:  60%|█████▉    | 174/291 [00:05<00:03, 36.71it/s]
Loading 0:  61%|██████    | 178/291 [00:05<00:03, 34.65it/s]
Loading 0:  63%|██████▎   | 182/291 [00:05<00:03, 35.89it/s]
Loading 0:  64%|██████▍   | 186/291 [00:05<00:04, 26.23it/s]
Loading 0:  65%|██████▌   | 190/291 [00:06<00:03, 25.91it/s]
Loading 0:  67%|██████▋   | 194/291 [00:06<00:03, 25.47it/s]
Loading 0:  69%|██████▉   | 201/291 [00:06<00:02, 33.46it/s]
Loading 0:  70%|███████   | 205/291 [00:06<00:02, 32.54it/s]
Loading 0:  72%|███████▏  | 210/291 [00:06<00:02, 35.92it/s]
Loading 0:  74%|███████▎  | 214/291 [00:06<00:02, 34.56it/s]
Loading 0:  75%|███████▌  | 219/291 [00:06<00:01, 37.75it/s]
Loading 0:  77%|███████▋  | 223/291 [00:06<00:01, 34.91it/s]
Loading 0:  78%|███████▊  | 227/291 [00:07<00:01, 35.62it/s]
Loading 0:  79%|███████▉  | 231/291 [00:07<00:01, 35.84it/s]
Loading 0:  81%|████████  | 235/291 [00:07<00:02, 26.52it/s]
Loading 0:  82%|████████▏ | 239/291 [00:07<00:02, 25.92it/s]
Loading 0:  85%|████████▍ | 246/291 [00:07<00:01, 33.30it/s]
Loading 0:  86%|████████▌ | 250/291 [00:07<00:01, 32.22it/s]
Loading 0:  88%|████████▊ | 255/291 [00:07<00:01, 35.91it/s]
Loading 0:  89%|████████▉ | 259/291 [00:08<00:00, 34.49it/s]
Loading 0:  91%|█████████ | 264/291 [00:08<00:00, 37.41it/s]
Loading 0:  92%|█████████▏| 268/291 [00:08<00:00, 34.82it/s]
Loading 0:  94%|█████████▍| 273/291 [00:08<00:00, 36.65it/s]
Loading 0:  95%|█████████▌| 277/291 [00:08<00:00, 34.15it/s]
Loading 0:  97%|█████████▋| 281/291 [00:08<00:00, 34.50it/s]
Loading 0:  98%|█████████▊| 286/291 [00:14<00:01,  2.57it/s]
Loading 0:  99%|█████████▉| 289/291 [00:14<00:00,  3.20it/s]
                                                            

Job chaiml-elo-alignment-run-3-v39-mkmlizer completed after 105.17s with status: succeeded
Stopping job with name chaiml-elo-alignment-run-3-v39-mkmlizer
Pipeline stage MKMLizer completed in 106.25s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-elo-alignment-run-3-v39
Waiting for inference service chaiml-elo-alignment-run-3-v39 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
Inference service chaiml-elo-alignment-run-3-v39 ready after 140.65488815307617s
Pipeline stage MKMLDeployer completed in 141.05s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1103174686431885s
Received healthy response to inference request in 1.9904253482818604s
Received healthy response to inference request in 1.6876401901245117s
Received healthy response to inference request in 1.5222489833831787s
Received healthy response to inference request in 2.1634466648101807s
5 requests
0 failed requests
5th percentile: 1.5553272247314454
10th percentile: 1.588405466079712
20th percentile: 1.654561948776245
30th percentile: 1.7481972217559814
40th percentile: 1.8693112850189209
50th percentile: 1.9904253482818604
60th percentile: 2.0383821964263915
70th percentile: 2.0863390445709227
80th percentile: 2.120943307876587
90th percentile: 2.142194986343384
95th percentile: 2.1528208255767822
99th percentile: 2.161321496963501
mean time: 1.894815731048584
Pipeline stage StressChecker completed in 10.33s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 7.71s
Shutdown handler de-registered
chaiml-elo-alignment-run-3_v39 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-elo-alignment-run-3-v39-profiler
Waiting for inference service chaiml-elo-alignment-run-3-v39-profiler to be ready
Inference service chaiml-elo-alignment-run-3-v39-profiler ready after 140.3865303993225s
Pipeline stage MKMLProfilerDeployer completed in 140.76s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-elo-alignment88f1022f9931f5f21848483e8e2833ed-deploxvw86:/code/chaiverse_profiler_1725483187 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-elo-alignment88f1022f9931f5f21848483e8e2833ed-deploxvw86 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725483187 && python profiles.py profile --best_of_n 16 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 512 --output_tokens 64 --summary /code/chaiverse_profiler_1725483187/summary.json'
kubectl exec -it chaiml-elo-alignment88f1022f9931f5f21848483e8e2833ed-deploxvw86 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725483187/summary.json'
Pipeline stage MKMLProfilerRunner completed in 829.67s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-elo-alignment-run-3-v39-profiler is running
Tearing down inference service chaiml-elo-alignment-run-3-v39-profiler
Service chaiml-elo-alignment-run-3-v39-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.98s
Shutdown handler de-registered
chaiml-elo-alignment-run-3_v39 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics