chaiml-elo-alignment-run-3

submission_id: chaiml-elo-alignment-run-3_v35
developer_uid: chai_backend_admin
best_of: 16
celo_rating: 1272.16
display_name: chaiml-elo-alignment-run-3_v3
family_friendly_score: 0.0
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
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: 11579
num_wins: 6479
ranking_group: single
status: torndown
submission_type: basic
timestamp: 2024-08-18T08:18:13+00:00
us_pacific_date: 2024-08-18
win_ratio: 0.55954745660247
Resubmit model
Running pipeline stage MKMLizer
Starting job with name chaiml-elo-alignment-run-3-v35-mkmlizer
Waiting for job on chaiml-elo-alignment-run-3-v35-mkmlizer to finish
chaiml-elo-alignment-run-3-v35-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-elo-alignment-run-3-v35-mkmlizer: ║     _____            __           __                                ║
chaiml-elo-alignment-run-3-v35-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-elo-alignment-run-3-v35-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-elo-alignment-run-3-v35-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-elo-alignment-run-3-v35-mkmlizer: ║       /___/                                                         ║
chaiml-elo-alignment-run-3-v35-mkmlizer: ║                                                                     ║
chaiml-elo-alignment-run-3-v35-mkmlizer: ║  Version: 0.9.11                                                    ║
chaiml-elo-alignment-run-3-v35-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-elo-alignment-run-3-v35-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-elo-alignment-run-3-v35-mkmlizer: ║                                                                     ║
chaiml-elo-alignment-run-3-v35-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-elo-alignment-run-3-v35-mkmlizer: ║  belonging to:                                                      ║
chaiml-elo-alignment-run-3-v35-mkmlizer: ║                                                                     ║
chaiml-elo-alignment-run-3-v35-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-elo-alignment-run-3-v35-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-elo-alignment-run-3-v35-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-elo-alignment-run-3-v35-mkmlizer: ║                                                                     ║
chaiml-elo-alignment-run-3-v35-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-elo-alignment-run-3-v35-mkmlizer: Downloaded to shared memory in 63.248s
chaiml-elo-alignment-run-3-v35-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpehjcbj4g, device:0
chaiml-elo-alignment-run-3-v35-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-elo-alignment-run-3-v35-mkmlizer: quantized model in 29.227s
chaiml-elo-alignment-run-3-v35-mkmlizer: Processed model ChaiML/elo_alignment_run_3 in 92.476s
chaiml-elo-alignment-run-3-v35-mkmlizer: creating bucket guanaco-mkml-models
chaiml-elo-alignment-run-3-v35-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-elo-alignment-run-3-v35-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v35
chaiml-elo-alignment-run-3-v35-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v35/config.json
chaiml-elo-alignment-run-3-v35-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v35/special_tokens_map.json
chaiml-elo-alignment-run-3-v35-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v35/tokenizer_config.json
chaiml-elo-alignment-run-3-v35-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v35/tokenizer.json
chaiml-elo-alignment-run-3-v35-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v35/flywheel_model.0.safetensors
chaiml-elo-alignment-run-3-v35-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:10, 26.06it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:07, 35.25it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:08, 33.27it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:07, 36.04it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:07, 33.56it/s]
Loading 0:  10%|█         | 30/291 [00:00<00:06, 37.95it/s]
Loading 0:  12%|█▏        | 34/291 [00:01<00:10, 24.96it/s]
Loading 0:  13%|█▎        | 38/291 [00:01<00:09, 26.50it/s]
Loading 0:  14%|█▍        | 42/291 [00:01<00:09, 25.06it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:08, 30.24it/s]
Loading 0:  18%|█▊        | 52/291 [00:01<00:07, 30.14it/s]
Loading 0:  20%|█▉        | 57/291 [00:01<00:07, 33.01it/s]
Loading 0:  21%|██        | 61/291 [00:01<00:07, 31.52it/s]
Loading 0:  23%|██▎       | 66/291 [00:02<00:06, 34.51it/s]
Loading 0:  24%|██▍       | 70/291 [00:02<00:06, 33.29it/s]
Loading 0:  25%|██▌       | 74/291 [00:02<00:06, 33.05it/s]
Loading 0:  27%|██▋       | 78/291 [00:02<00:06, 33.13it/s]
Loading 0:  28%|██▊       | 82/291 [00:02<00:09, 22.95it/s]
Loading 0:  29%|██▉       | 85/291 [00:02<00:08, 24.10it/s]
Loading 0:  31%|███       | 90/291 [00:03<00:07, 28.24it/s]
Loading 0:  32%|███▏      | 94/291 [00:03<00:06, 28.75it/s]
Loading 0:  34%|███▍      | 99/291 [00:03<00:06, 31.65it/s]
Loading 0:  35%|███▌      | 103/291 [00:03<00:06, 31.25it/s]
Loading 0:  37%|███▋      | 108/291 [00:03<00:05, 34.33it/s]
Loading 0:  38%|███▊      | 112/291 [00:03<00:05, 33.09it/s]
Loading 0:  40%|███▉      | 116/291 [00:03<00:05, 33.10it/s]
Loading 0:  42%|████▏     | 122/291 [00:03<00:04, 37.45it/s]
Loading 0:  44%|████▎     | 127/291 [00:04<00:04, 35.31it/s]
Loading 0:  46%|████▌     | 133/291 [00:04<00:05, 29.62it/s]
Loading 0:  47%|████▋     | 137/291 [00:04<00:05, 29.79it/s]
Loading 0:  48%|████▊     | 141/291 [00:04<00:05, 27.40it/s]
Loading 0:  51%|█████     | 147/291 [00:04<00:04, 32.15it/s]
Loading 0:  52%|█████▏    | 151/291 [00:04<00:04, 31.61it/s]
Loading 0:  54%|█████▎    | 156/291 [00:05<00:03, 34.05it/s]
Loading 0:  55%|█████▍    | 160/291 [00:05<00:03, 32.88it/s]
Loading 0:  57%|█████▋    | 165/291 [00:05<00:03, 35.29it/s]
Loading 0:  58%|█████▊    | 169/291 [00:05<00:03, 33.75it/s]
Loading 0:  60%|█████▉    | 174/291 [00:05<00:03, 35.73it/s]
Loading 0:  61%|██████    | 178/291 [00:05<00:03, 33.02it/s]
Loading 0:  63%|██████▎   | 184/291 [00:05<00:02, 38.80it/s]
Loading 0:  65%|██████▍   | 189/291 [00:06<00:04, 23.54it/s]
Loading 0:  67%|██████▋   | 194/291 [00:06<00:03, 25.19it/s]
Loading 0:  69%|██████▉   | 201/291 [00:06<00:02, 31.31it/s]
Loading 0:  70%|███████   | 205/291 [00:06<00:02, 31.12it/s]
Loading 0:  72%|███████▏  | 210/291 [00:06<00:02, 33.71it/s]
Loading 0:  74%|███████▎  | 214/291 [00:06<00:02, 32.92it/s]
Loading 0:  75%|███████▌  | 219/291 [00:06<00:02, 35.34it/s]
Loading 0:  77%|███████▋  | 223/291 [00:07<00:01, 34.03it/s]
Loading 0:  78%|███████▊  | 227/291 [00:07<00:01, 34.07it/s]
Loading 0:  79%|███████▉  | 231/291 [00:07<00:01, 33.28it/s]
Loading 0:  81%|████████  | 235/291 [00:07<00:02, 24.59it/s]
Loading 0:  82%|████████▏ | 239/291 [00:07<00:02, 24.82it/s]
Loading 0:  85%|████████▍ | 246/291 [00:07<00:01, 32.56it/s]
Loading 0:  86%|████████▌ | 250/291 [00:08<00:01, 31.84it/s]
Loading 0:  88%|████████▊ | 255/291 [00:08<00:01, 35.04it/s]
Loading 0:  89%|████████▉ | 259/291 [00:08<00:00, 33.80it/s]
Loading 0:  91%|█████████ | 264/291 [00:08<00:00, 36.53it/s]
Loading 0:  92%|█████████▏| 268/291 [00:08<00:00, 34.82it/s]
Loading 0:  94%|█████████▍| 273/291 [00:08<00:00, 36.99it/s]
Loading 0:  95%|█████████▌| 277/291 [00:08<00:00, 34.97it/s]
Loading 0:  97%|█████████▋| 281/291 [00:08<00:00, 34.65it/s]
Loading 0:  98%|█████████▊| 286/291 [00:14<00:01,  2.57it/s]
Loading 0:  99%|█████████▉| 289/291 [00:14<00:00,  3.21it/s]
                                                            
Job chaiml-elo-alignment-run-3-v35-mkmlizer completed after 116.06s with status: succeeded
Stopping job with name chaiml-elo-alignment-run-3-v35-mkmlizer
Pipeline stage MKMLizer completed in 117.14s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-elo-alignment-run-3-v35
Waiting for inference service chaiml-elo-alignment-run-3-v35 to be ready
Inference service chaiml-elo-alignment-run-3-v35 ready after 232.12633848190308s
Pipeline stage ISVCDeployer completed in 233.04s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.03165340423584s
Received healthy response to inference request in 1.855985164642334s
Received healthy response to inference request in 1.6699755191802979s
Received healthy response to inference request in 1.5781359672546387s
Received healthy response to inference request in 1.5137817859649658s
5 requests
0 failed requests
5th percentile: 1.5266526222229004
10th percentile: 1.539523458480835
20th percentile: 1.565265130996704
30th percentile: 1.5965038776397704
40th percentile: 1.6332396984100341
50th percentile: 1.6699755191802979
60th percentile: 1.7443793773651124
70th percentile: 1.8187832355499267
80th percentile: 1.8911188125610352
90th percentile: 1.9613861083984374
95th percentile: 1.9965197563171386
99th percentile: 2.0246266746520996
mean time: 1.7299063682556153
Pipeline stage StressChecker completed in 9.36s
chaiml-elo-alignment-run-3_v35 status is now deployed due to DeploymentManager action
chaiml-elo-alignment-run-3_v35 status is now inactive due to auto deactivation removed underperforming models
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage %s skipped, reason=%s
Pipeline stage MKMLProfilerTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-elo-alignment-run-3-v35-profiler
Ignoring service chaiml-elo-alignment-run-3-v35-profiler already deployed
Waiting for inference service chaiml-elo-alignment-run-3-v35-profiler to be ready
Inference service chaiml-elo-alignment-run-3-v35-profiler ready after 10.274394035339355s
Pipeline stage MKMLProfilerDeployer completed in 11.29s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/scripts tenant-chaiml-guanaco/chaiml-elo-alignment5a749c5ef4356ab7a18a89196786d5f0-deplor7snf:/code/chaiverse_profiler_1725175260
kubectl exec -it chaiml-elo-alignment5a749c5ef4356ab7a18a89196786d5f0-deplor7snf -- sh -c 'cd /code/chaiverse_profiler_1725175260 && chmod +x profiles.py && python profiles.py profile --best_of_n 16 --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_1725175260/summary.json'
kubectl exec -it chaiml-elo-alignment5a749c5ef4356ab7a18a89196786d5f0-deplor7snf -- bash -c 'cat /code/chaiverse_profiler_1725175260/summary.json'
Pipeline stage MKMLProfilerRunner completed in 535.06s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-elo-alignment-run-3-v35-profiler is running
Tearing down inference service chaiml-elo-alignment-run-3-v35-profiler
Service chaiml-elo-alignment-run-3-v35-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 3.43s
chaiml-elo-alignment-run-3_v35 status is now torndown due to DeploymentManager action