chaiml-elo-alignment-run-3

developer_uid: azuruce

submission_id: chaiml-elo-alignment-run-3_v46

model_name: chaiml-elo-alignment-run-3_v46

model_group: ChaiML/elo_alignment_run

status: torndown

timestamp: 2024-09-20T16:48:15+00:00

num_battles: 11299

num_wins: 5885

celo_rating: 1261.94

family_friendly_score: 0.0

submission_type: basic

model_repo: ChaiML/elo_alignment_run_3

model_architecture: LlamaForCausalLM

model_num_parameters: 8030261248.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6432730970171059, 'latency_mean': 1.5544833171367645, 'latency_p50': 1.196886420249939, 'latency_p90': 1.3558251619338988}, {'batch_size': 4, 'throughput': 1.85547338612672, 'latency_mean': 2.1477213490009306, 'latency_p50': 2.1214280128479004, 'latency_p90': 2.420103931427002}, {'batch_size': 5, 'throughput': 1.9733469735643365, 'latency_mean': 2.5159652066230773, 'latency_p50': 2.522880434989929, 'latency_p90': 2.7669642210006713}, {'batch_size': 8, 'throughput': 2.2135926980548075, 'latency_mean': 3.5862022531032562, 'latency_p50': 3.5807937383651733, 'latency_p90': 4.074175095558166}, {'batch_size': 10, 'throughput': 2.2743933223055848, 'latency_mean': 4.361618480682373, 'latency_p50': 4.360531806945801, 'latency_p90': 4.910746932029724}, {'batch_size': 12, 'throughput': 2.3072533448038532, 'latency_mean': 5.153180305957794, 'latency_p50': 5.111233115196228, 'latency_p90': 5.897446084022522}, {'batch_size': 15, 'throughput': 2.3142002642322796, 'latency_mean': 6.392674962282181, 'latency_p50': 6.3463945388793945, 'latency_p90': 7.193436145782471}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-elo-alignment-run-3_v46

is_internal_developer: True

language_model: ChaiML/elo_alignment_run_3

model_size: 8B

ranking_group: single

throughput_3p7s: 2.24

us_pacific_date: 2024-09-20

win_ratio: 0.5208425524382688

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, '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-v46-mkmlizer
Waiting for job on chaiml-elo-alignment-run-3-v46-mkmlizer to finish
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-elo-alignment-run-3-v46-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-elo-alignment-run-3-v46-mkmlizer: ║     _____            __           __                                ║
chaiml-elo-alignment-run-3-v46-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-elo-alignment-run-3-v46-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-elo-alignment-run-3-v46-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-elo-alignment-run-3-v46-mkmlizer: ║       /___/                                                         ║
chaiml-elo-alignment-run-3-v46-mkmlizer: ║                                                                     ║
chaiml-elo-alignment-run-3-v46-mkmlizer: ║  Version: 0.10.1                                                    ║
chaiml-elo-alignment-run-3-v46-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-elo-alignment-run-3-v46-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-elo-alignment-run-3-v46-mkmlizer: ║                                                                     ║
chaiml-elo-alignment-run-3-v46-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-elo-alignment-run-3-v46-mkmlizer: ║  belonging to:                                                      ║
chaiml-elo-alignment-run-3-v46-mkmlizer: ║                                                                     ║
chaiml-elo-alignment-run-3-v46-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-elo-alignment-run-3-v46-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-elo-alignment-run-3-v46-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-elo-alignment-run-3-v46-mkmlizer: ║                                                                     ║
chaiml-elo-alignment-run-3-v46-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-elo-alignment-run-3-v46-mkmlizer: Downloaded to shared memory in 44.681s
chaiml-elo-alignment-run-3-v46-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_rlq5c14, device:0
chaiml-elo-alignment-run-3-v46-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
chaiml-elo-alignment-run-3-v46-mkmlizer: quantized model in 29.028s
chaiml-elo-alignment-run-3-v46-mkmlizer: Processed model ChaiML/elo_alignment_run_3 in 73.710s
chaiml-elo-alignment-run-3-v46-mkmlizer: creating bucket guanaco-mkml-models
chaiml-elo-alignment-run-3-v46-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-elo-alignment-run-3-v46-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v46
chaiml-elo-alignment-run-3-v46-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v46/config.json
chaiml-elo-alignment-run-3-v46-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v46/special_tokens_map.json
chaiml-elo-alignment-run-3-v46-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v46/tokenizer_config.json
chaiml-elo-alignment-run-3-v46-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v46/tokenizer.json
chaiml-elo-alignment-run-3-v46-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v46/flywheel_model.0.safetensors
chaiml-elo-alignment-run-3-v46-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:11, 24.37it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:07, 35.11it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:08, 32.52it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:07, 35.58it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:07, 34.07it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:06, 40.80it/s]
Loading 0:  12%|█▏        | 36/291 [00:01<00:11, 21.66it/s]
Loading 0:  14%|█▍        | 41/291 [00:01<00:10, 24.05it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:07, 31.00it/s]
Loading 0:  18%|█▊        | 52/291 [00:01<00:07, 31.06it/s]
Loading 0:  20%|█▉        | 57/291 [00:01<00:06, 34.43it/s]
Loading 0:  21%|██        | 61/291 [00:01<00:06, 34.03it/s]
Loading 0:  23%|██▎       | 66/291 [00:02<00:06, 36.36it/s]
Loading 0:  24%|██▍       | 70/291 [00:02<00:06, 35.03it/s]
Loading 0:  25%|██▌       | 74/291 [00:02<00:06, 35.57it/s]
Loading 0:  27%|██▋       | 78/291 [00:02<00:05, 36.16it/s]
Loading 0:  28%|██▊       | 82/291 [00:02<00:08, 23.46it/s]
Loading 0:  30%|██▉       | 86/291 [00:02<00:07, 26.20it/s]
Loading 0:  31%|███▏      | 91/291 [00:02<00:06, 29.10it/s]
Loading 0:  33%|███▎      | 96/291 [00:03<00:05, 33.12it/s]
Loading 0:  34%|███▍      | 100/291 [00:03<00:05, 32.18it/s]
Loading 0:  36%|███▌      | 105/291 [00:03<00:05, 35.59it/s]
Loading 0:  37%|███▋      | 109/291 [00:03<00:05, 34.45it/s]
Loading 0:  39%|███▉      | 113/291 [00:03<00:05, 35.21it/s]
Loading 0:  40%|████      | 117/291 [00:03<00:05, 34.10it/s]
Loading 0:  42%|████▏     | 122/291 [00:03<00:04, 36.54it/s]
Loading 0:  44%|████▎     | 127/291 [00:03<00:04, 35.42it/s]
Loading 0:  46%|████▌     | 133/291 [00:04<00:05, 29.63it/s]
Loading 0:  47%|████▋     | 137/291 [00:04<00:05, 29.61it/s]
Loading 0:  48%|████▊     | 141/291 [00:04<00:05, 28.56it/s]
Loading 0:  51%|█████     | 147/291 [00:04<00:04, 34.14it/s]
Loading 0:  52%|█████▏    | 151/291 [00:04<00:04, 33.72it/s]
Loading 0:  54%|█████▎    | 156/291 [00:04<00:03, 36.20it/s]
Loading 0:  55%|█████▍    | 160/291 [00:04<00:03, 35.47it/s]
Loading 0:  57%|█████▋    | 165/291 [00:05<00:03, 38.62it/s]
Loading 0:  58%|█████▊    | 169/291 [00:05<00:03, 37.14it/s]
Loading 0:  60%|█████▉    | 174/291 [00:05<00:03, 38.86it/s]
Loading 0:  61%|██████    | 178/291 [00:05<00:03, 35.81it/s]
Loading 0:  64%|██████▎   | 185/291 [00:05<00:02, 40.59it/s]
Loading 0:  65%|██████▌   | 190/291 [00:05<00:03, 25.61it/s]
Loading 0:  67%|██████▋   | 194/291 [00:06<00:03, 25.41it/s]
Loading 0:  69%|██████▉   | 201/291 [00:06<00:02, 32.70it/s]
Loading 0:  70%|███████   | 205/291 [00:06<00:02, 32.40it/s]
Loading 0:  72%|███████▏  | 210/291 [00:06<00:02, 34.99it/s]
Loading 0:  74%|███████▎  | 214/291 [00:06<00:02, 34.23it/s]
Loading 0:  75%|███████▌  | 219/291 [00:06<00:01, 37.40it/s]
Loading 0:  77%|███████▋  | 223/291 [00:06<00:01, 36.08it/s]
Loading 0:  78%|███████▊  | 227/291 [00:06<00:01, 35.41it/s]
Loading 0:  79%|███████▉  | 231/291 [00:07<00:01, 35.58it/s]
Loading 0:  81%|████████  | 235/291 [00:07<00:02, 25.50it/s]
Loading 0:  82%|████████▏ | 239/291 [00:07<00:02, 24.60it/s]
Loading 0:  85%|████████▍ | 246/291 [00:07<00:01, 32.92it/s]
Loading 0:  86%|████████▌ | 250/291 [00:07<00:01, 33.21it/s]
Loading 0:  88%|████████▊ | 255/291 [00:07<00:00, 36.80it/s]
Loading 0:  89%|████████▉ | 260/291 [00:07<00:00, 37.13it/s]
Loading 0:  91%|█████████ | 264/291 [00:08<00:00, 37.36it/s]
Loading 0:  92%|█████████▏| 268/291 [00:08<00:00, 36.21it/s]
Loading 0:  94%|█████████▍| 273/291 [00:08<00:00, 39.10it/s]
Loading 0:  96%|█████████▌| 278/291 [00:08<00:00, 38.77it/s]
Loading 0:  97%|█████████▋| 282/291 [00:08<00:00, 38.11it/s]
Loading 0:  98%|█████████▊| 286/291 [00:14<00:02,  2.44it/s]
Loading 0:  99%|█████████▉| 289/291 [00:14<00:00,  3.07it/s]
                                                            
Job chaiml-elo-alignment-run-3-v46-mkmlizer completed after 103.99s with status: succeeded
Stopping job with name chaiml-elo-alignment-run-3-v46-mkmlizer
Pipeline stage MKMLizer completed in 104.90s
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-v46
Waiting for inference service chaiml-elo-alignment-run-3-v46 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
Inference service chaiml-elo-alignment-run-3-v46 ready after 221.59741377830505s
Pipeline stage MKMLDeployer completed in 222.05s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.200230360031128s
Received healthy response to inference request in 1.3316314220428467s
Received healthy response to inference request in 1.3294386863708496s
Received healthy response to inference request in 1.4610912799835205s
Received healthy response to inference request in 1.3952152729034424s
5 requests
0 failed requests
5th percentile: 1.3298772335052491
10th percentile: 1.3303157806396484
20th percentile: 1.3311928749084472
30th percentile: 1.3443481922149658
40th percentile: 1.369781732559204
50th percentile: 1.3952152729034424
60th percentile: 1.4215656757354735
70th percentile: 1.447916078567505
80th percentile: 1.6089190959930422
90th percentile: 1.904574728012085
95th percentile: 2.0524025440216063
99th percentile: 2.1706647968292234
mean time: 1.5435214042663574
Pipeline stage StressChecker completed in 8.50s
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 6.77s
Shutdown handler de-registered
chaiml-elo-alignment-run-3_v46 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 0.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-elo-alignment-run-3-v46-profiler
Waiting for inference service chaiml-elo-alignment-run-3-v46-profiler to be ready
Inference service chaiml-elo-alignment-run-3-v46-profiler ready after 220.54040217399597s
Pipeline stage MKMLProfilerDeployer completed in 220.91s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-elo-alignment87e98b1b807491f86c0b269a05b1896d-deplodxlmw:/code/chaiverse_profiler_1726851518 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-elo-alignment87e98b1b807491f86c0b269a05b1896d-deplodxlmw --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726851518 && python profiles.py profile --best_of_n 8 --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 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1726851518/summary.json'
kubectl exec -it chaiml-elo-alignment87e98b1b807491f86c0b269a05b1896d-deplodxlmw --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726851518/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-elo-alignment87e98b1b807491f86c0b269a05b1896d-deplodxlmw:/code/chaiverse_profiler_1726852218 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-elo-alignment87e98b1b807491f86c0b269a05b1896d-deplodxlmw --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726852218 && python profiles.py profile --best_of_n 8 --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 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1726852218/summary.json'
kubectl exec -it chaiml-elo-alignment87e98b1b807491f86c0b269a05b1896d-deplodxlmw --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726852218/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1578.48s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-elo-alignment-run-3-v46-profiler is running
Tearing down inference service chaiml-elo-alignment-run-3-v46-profiler
Service chaiml-elo-alignment-run-3-v46-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.05s
Shutdown handler de-registered
chaiml-elo-alignment-run-3_v46 status is now inactive due to auto deactivation removed underperforming models
chaiml-elo-alignment-run-3_v46 status is now torndown due to DeploymentManager action
run pipeline stage %s
Running pipeline stage MKMLModelDeleter
chaiml-elo-alignment-run-3_v45 status is now torndown due to DeploymentManager action
admin requested tearing down of chaiml-virgo-edit-v1-1e5_v1
Pipeline stage MKMLModelDeleter completed in 3.41s
Pipeline stage %s skipped, reason=%s
run pipeline stage %s
Pipeline stage MKMLDeleter completed in 3.40s
Pipeline stage %s skipped, reason=%s
chaiml-elo-alignment-run-3_v46 status is now torndown due to DeploymentManager action
Running pipeline stage MKMLDeleter
Pipeline stage %s skipped, reason=%s
run pipeline stage %s
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
Shutdown handler de-registered
admin requested tearing down of chaiml-virgo-edit-v1-1e5_v2
Running pipeline stage MKMLModelDeleter
run pipeline stage %s
chaiml-elo-alignment-run-3_v45 status is now torndown due to DeploymentManager action
Pipeline stage MKMLModelDeleter completed in 4.01s
Pipeline stage MKMLDeleter completed in 4.01s
Pipeline stage %s skipped, reason=%s
run pipeline stage %s
run pipeline %s
chaiml-elo-alignment-run-3_v46 status is now torndown due to DeploymentManager action
Shutdown handler not registered because Python interpreter is not running in the main thread
Pipeline stage %s skipped, reason=%s
admin requested tearing down of chaiml-virgo-edit-v1-1e5_v1