chaiml-albert-dpo-0912-v_1751

submission_id: chaiml-albert-dpo-0912-v_1751_v5

developer_uid: azuruce

alignment_samples: 11652

alignment_score: 2.197403872932366

best_of: 8

celo_rating: 1240.17

display_name: virgo-edit-original

formatter: {'memory_template': 'Bot Name: {bot_name}\n####\n', 'prompt_template': '', 'bot_template': 'Bot: {message}\n', 'user_template': 'User: {message}\n', 'response_template': 'Bot:', 'truncate_by_message': False}

generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '###', 'Bot:', 'User:', 'You:', '<|im_end|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

gpu_counts: {'NVIDIA RTX A5000': 1}

is_internal_developer: True

language_model: ChaiML/albert_dpo_0912_virgo_edit_original

latencies: [{'batch_size': 1, 'throughput': 0.6103073795860545, 'latency_mean': 1.6384541594982147, 'latency_p50': 1.6342464685440063, 'latency_p90': 1.7974900722503662}, {'batch_size': 3, 'throughput': 1.0664555715694943, 'latency_mean': 2.8029837572574614, 'latency_p50': 2.806893467903137, 'latency_p90': 3.1248981237411497}, {'batch_size': 5, 'throughput': 1.2305248930756065, 'latency_mean': 4.040937011241913, 'latency_p50': 4.056117057800293, 'latency_p90': 4.5505211353302}, {'batch_size': 6, 'throughput': 1.1954030280735686, 'latency_mean': 5.004104830026627, 'latency_p50': 5.021663188934326, 'latency_p90': 5.6827120065689085}, {'batch_size': 10, 'throughput': 1.2036666239502167, 'latency_mean': 8.259669238328934, 'latency_p50': 8.336244463920593, 'latency_p90': 9.274081993103028}]

max_input_tokens: 1024

max_output_tokens: 64

model_architecture: MistralForCausalLM

model_group: ChaiML/albert_dpo_0912_v

model_name: virgo-edit-original

model_num_parameters: 12772070400.0

model_repo: ChaiML/albert_dpo_0912_virgo_edit_original

model_size: 13B

num_battles: 11651

num_wins: 5730

propriety_score: 0.7217473884140551

propriety_total_count: 1053.0

ranking_group: single

status: inactive

submission_type: basic

throughput_3p7s: 1.2

timestamp: 2024-09-15T05:34:29+00:00

us_pacific_date: 2024-09-14

win_ratio: 0.4918032786885246

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-albert-dpo-0912-v-1751-v5-mkmlizer
Waiting for job on chaiml-albert-dpo-0912-v-1751-v5-mkmlizer to finish
chaiml-albert-dpo-0912-v-1751-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-albert-dpo-0912-v-1751-v5-mkmlizer: ║     _____            __           __                                ║
chaiml-albert-dpo-0912-v-1751-v5-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-albert-dpo-0912-v-1751-v5-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-albert-dpo-0912-v-1751-v5-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-albert-dpo-0912-v-1751-v5-mkmlizer: ║       /___/                                                         ║
chaiml-albert-dpo-0912-v-1751-v5-mkmlizer: ║                                                                     ║
chaiml-albert-dpo-0912-v-1751-v5-mkmlizer: ║  Version: 0.10.1                                                    ║
chaiml-albert-dpo-0912-v-1751-v5-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-albert-dpo-0912-v-1751-v5-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-albert-dpo-0912-v-1751-v5-mkmlizer: ║                                                                     ║
chaiml-albert-dpo-0912-v-1751-v5-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-albert-dpo-0912-v-1751-v5-mkmlizer: ║  belonging to:                                                      ║
chaiml-albert-dpo-0912-v-1751-v5-mkmlizer: ║                                                                     ║
chaiml-albert-dpo-0912-v-1751-v5-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-albert-dpo-0912-v-1751-v5-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-albert-dpo-0912-v-1751-v5-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-albert-dpo-0912-v-1751-v5-mkmlizer: ║                                                                     ║
chaiml-albert-dpo-0912-v-1751-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-albert-dpo-0912-v-1751-v5-mkmlizer: Downloaded to shared memory in 55.399s
chaiml-albert-dpo-0912-v-1751-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpvk_qu4v8, device:0
chaiml-albert-dpo-0912-v-1751-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-albert-dpo-0912-v-1751-v5-mkmlizer: quantized model in 40.882s
chaiml-albert-dpo-0912-v-1751-v5-mkmlizer: Processed model ChaiML/albert_dpo_0912_virgo_edit_original in 96.281s
chaiml-albert-dpo-0912-v-1751-v5-mkmlizer: creating bucket guanaco-mkml-models
chaiml-albert-dpo-0912-v-1751-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-albert-dpo-0912-v-1751-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-1751-v5
chaiml-albert-dpo-0912-v-1751-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-1751-v5/config.json
chaiml-albert-dpo-0912-v-1751-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-1751-v5/special_tokens_map.json
chaiml-albert-dpo-0912-v-1751-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-1751-v5/tokenizer_config.json
chaiml-albert-dpo-0912-v-1751-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-1751-v5/tokenizer.json
chaiml-albert-dpo-0912-v-1751-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-1751-v5/flywheel_model.0.safetensors
chaiml-albert-dpo-0912-v-1751-v5-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 23.05it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 28.54it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:14, 24.49it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:09, 35.91it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:16, 20.54it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:13, 25.23it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:12, 26.92it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:11, 28.85it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:11, 28.14it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 30.73it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 29.52it/s]
Loading 0:  15%|█▌        | 56/363 [00:02<00:10, 30.26it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 26.16it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:13, 22.47it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:09, 29.66it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:09, 29.04it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 28.29it/s]
Loading 0:  23%|██▎       | 84/363 [00:03<00:08, 31.13it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:09, 29.57it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:08, 32.12it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:08, 30.51it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:10, 24.98it/s]
Loading 0:  29%|██▊       | 104/363 [00:03<00:11, 22.04it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:08, 29.09it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:08, 28.42it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:07, 31.50it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:07, 30.35it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 32.11it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 29.73it/s]
Loading 0:  38%|███▊      | 137/363 [00:04<00:07, 30.24it/s]
Loading 0:  39%|███▉      | 141/363 [00:04<00:06, 32.06it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:10, 21.66it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:10, 20.98it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:07, 27.77it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:07, 26.96it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 29.17it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:06, 27.96it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 30.63it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 29.28it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 24.08it/s]
Loading 0:  51%|█████     | 185/363 [00:06<00:08, 21.26it/s]
Loading 0:  53%|█████▎    | 192/363 [00:06<00:06, 28.11it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 27.48it/s]
Loading 0:  55%|█████▌    | 201/363 [00:07<00:05, 29.88it/s]
Loading 0:  56%|█████▋    | 205/363 [00:07<00:05, 28.82it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:04, 31.58it/s]
Loading 0:  59%|█████▉    | 214/363 [00:07<00:04, 30.27it/s]
Loading 0:  60%|██████    | 218/363 [00:07<00:04, 29.20it/s]
Loading 0:  61%|██████▏   | 223/363 [00:08<00:05, 25.52it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:05, 24.21it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:05, 22.95it/s]
Loading 0:  65%|██████▌   | 237/363 [00:08<00:04, 29.31it/s]
Loading 0:  66%|██████▋   | 241/363 [00:08<00:04, 28.39it/s]
Loading 0:  68%|██████▊   | 246/363 [00:08<00:03, 30.88it/s]
Loading 0:  69%|██████▉   | 250/363 [00:08<00:03, 29.44it/s]
Loading 0:  70%|███████   | 255/363 [00:09<00:03, 31.92it/s]
Loading 0:  71%|███████▏  | 259/363 [00:09<00:03, 29.64it/s]
Loading 0:  72%|███████▏  | 263/363 [00:09<00:04, 24.57it/s]
Loading 0:  73%|███████▎  | 266/363 [00:09<00:04, 21.40it/s]
Loading 0:  75%|███████▌  | 273/363 [00:09<00:03, 28.18it/s]
Loading 0:  76%|███████▋  | 277/363 [00:10<00:03, 27.70it/s]
Loading 0:  78%|███████▊  | 282/363 [00:10<00:02, 30.38it/s]
Loading 0:  79%|███████▉  | 286/363 [00:10<00:02, 29.44it/s]
Loading 0:  80%|████████  | 291/363 [00:10<00:02, 32.24it/s]
Loading 0:  81%|████████▏ | 295/363 [00:10<00:02, 29.64it/s]
Loading 0:  82%|████████▏ | 299/363 [00:10<00:02, 29.55it/s]
Loading 0:  84%|████████▎ | 304/363 [00:10<00:02, 25.66it/s]
Loading 0:  85%|████████▍ | 307/363 [00:11<00:02, 24.12it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 23.23it/s]
Loading 0:  88%|████████▊ | 318/363 [00:11<00:01, 29.70it/s]
Loading 0:  89%|████████▊ | 322/363 [00:11<00:01, 28.64it/s]
Loading 0:  90%|█████████ | 327/363 [00:11<00:01, 31.50it/s]
Loading 0:  91%|█████████ | 331/363 [00:11<00:01, 30.02it/s]
Loading 0:  93%|█████████▎| 336/363 [00:12<00:00, 32.29it/s]
Loading 0:  94%|█████████▎| 340/363 [00:12<00:00, 29.78it/s]
Loading 0:  95%|█████████▍| 344/363 [00:19<00:09,  1.98it/s]
Loading 0:  96%|█████████▌| 348/363 [00:19<00:05,  2.65it/s]
Loading 0:  97%|█████████▋| 353/363 [00:19<00:02,  3.85it/s]
Loading 0:  98%|█████████▊| 357/363 [00:19<00:01,  4.98it/s]
Loading 0: 100%|█████████▉| 362/363 [00:19<00:00,  7.09it/s]
                                                            
Job chaiml-albert-dpo-0912-v-1751-v5-mkmlizer completed after 125.29s with status: succeeded
Stopping job with name chaiml-albert-dpo-0912-v-1751-v5-mkmlizer
Pipeline stage MKMLizer completed in 126.30s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-albert-dpo-0912-v-1751-v5
Waiting for inference service chaiml-albert-dpo-0912-v-1751-v5 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
Inference service chaiml-albert-dpo-0912-v-1751-v5 ready after 160.57867789268494s
Pipeline stage MKMLDeployer completed in 161.03s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.282614231109619s
Received healthy response to inference request in 2.0914151668548584s
Received healthy response to inference request in 2.362426280975342s
Received healthy response to inference request in 2.561598300933838s
Received healthy response to inference request in 1.9885072708129883s
5 requests
0 failed requests
5th percentile: 2.0090888500213624
10th percentile: 2.0296704292297365
20th percentile: 2.0708335876464843
30th percentile: 2.1296549797058106
40th percentile: 2.2061346054077147
50th percentile: 2.282614231109619
60th percentile: 2.3145390510559083
70th percentile: 2.3464638710021974
80th percentile: 2.402260684967041
90th percentile: 2.4819294929504396
95th percentile: 2.5217638969421388
99th percentile: 2.553631420135498
mean time: 2.2573122501373293
Pipeline stage StressChecker completed in 12.12s
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 5.52s
Shutdown handler de-registered
chaiml-albert-dpo-0912-v_1751_v5 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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-albert-dpo-0912-v-1751-v5-profiler
Waiting for inference service chaiml-albert-dpo-0912-v-1751-v5-profiler to be ready
Inference service chaiml-albert-dpo-0912-v-1751-v5-profiler ready after 170.42306065559387s
Pipeline stage MKMLProfilerDeployer completed in 170.78s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-albert-dpo-099ee15309565a00974d84ef5ac712c26c-deploqqjbb:/code/chaiverse_profiler_1726379007 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-albert-dpo-099ee15309565a00974d84ef5ac712c26c-deploqqjbb --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726379007 && 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_1726379007/summary.json'
kubectl exec -it chaiml-albert-dpo-099ee15309565a00974d84ef5ac712c26c-deploqqjbb --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726379007/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1018.85s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-albert-dpo-0912-v-1751-v5-profiler is running
Tearing down inference service chaiml-albert-dpo-0912-v-1751-v5-profiler
Service chaiml-albert-dpo-0912-v-1751-v5-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.06s
Shutdown handler de-registered
chaiml-albert-dpo-0912-v_1751_v5 status is now inactive due to auto deactivation removed underperforming models