chaiml-albert-dpo-0912-v_5607

submission_id: chaiml-albert-dpo-0912-v_5607_v2

developer_uid: chai_backend_admin

alignment_samples: 14792

alignment_score: -0.7313047459005242

best_of: 8

celo_rating: 1249.89

display_name: virgo_edit_variety_random

formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', '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_variety_random

latencies: [{'batch_size': 1, 'throughput': 0.6193673931781079, 'latency_mean': 1.614487271308899, 'latency_p50': 1.608641266822815, 'latency_p90': 1.7930634498596192}, {'batch_size': 3, 'throughput': 1.0662350447874918, 'latency_mean': 2.7996656703948974, 'latency_p50': 2.7921046018600464, 'latency_p90': 3.0524545192718504}, {'batch_size': 5, 'throughput': 1.2235923372415523, 'latency_mean': 4.074634031057358, 'latency_p50': 4.064963340759277, 'latency_p90': 4.538066053390502}, {'batch_size': 6, 'throughput': 1.2540391001531916, 'latency_mean': 4.7705660557746885, 'latency_p50': 4.794060468673706, 'latency_p90': 5.475505065917969}, {'batch_size': 8, 'throughput': 1.2336608859230003, 'latency_mean': 6.44666535615921, 'latency_p50': 6.408973574638367, 'latency_p90': 7.261414217948913}, {'batch_size': 10, 'throughput': 1.2018208185522927, 'latency_mean': 8.28063536643982, 'latency_p50': 8.300958752632141, 'latency_p90': 9.267731881141662}]

max_input_tokens: 1024

max_output_tokens: 64

model_architecture: MistralForCausalLM

model_group: ChaiML/albert_dpo_0912_v

model_name: virgo_edit_variety_random

model_num_parameters: 12772070400.0

model_repo: ChaiML/albert_dpo_0912_virgo_edit_variety_random

model_size: 13B

num_battles: 14788

num_wins: 7423

propriety_score: 0.7231638418079096

propriety_total_count: 1239.0

ranking_group: single

status: inactive

submission_type: basic

throughput_3p7s: 1.19

timestamp: 2024-09-13T21:37:22+00:00

us_pacific_date: 2024-09-13

win_ratio: 0.5019610494995943

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-5607-v2-mkmlizer
Waiting for job on chaiml-albert-dpo-0912-v-5607-v2-mkmlizer to finish
chaiml-albert-dpo-0912-v-5607-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-albert-dpo-0912-v-5607-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-albert-dpo-0912-v-5607-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-albert-dpo-0912-v-5607-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-albert-dpo-0912-v-5607-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-albert-dpo-0912-v-5607-v2-mkmlizer: ║       /___/                                                         ║
chaiml-albert-dpo-0912-v-5607-v2-mkmlizer: ║                                                                     ║
chaiml-albert-dpo-0912-v-5607-v2-mkmlizer: ║  Version: 0.10.1                                                    ║
chaiml-albert-dpo-0912-v-5607-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-albert-dpo-0912-v-5607-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-albert-dpo-0912-v-5607-v2-mkmlizer: ║                                                                     ║
chaiml-albert-dpo-0912-v-5607-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-albert-dpo-0912-v-5607-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-albert-dpo-0912-v-5607-v2-mkmlizer: ║                                                                     ║
chaiml-albert-dpo-0912-v-5607-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-albert-dpo-0912-v-5607-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-albert-dpo-0912-v-5607-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-albert-dpo-0912-v-5607-v2-mkmlizer: ║                                                                     ║
chaiml-albert-dpo-0912-v-5607-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-albert-dpo-0912-v-5607-v2-mkmlizer: Downloaded to shared memory in 75.523s
chaiml-albert-dpo-0912-v-5607-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp3umooisr, device:0
chaiml-albert-dpo-0912-v-5607-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-albert-dpo-0912-v-5607-v2-mkmlizer: quantized model in 40.565s
chaiml-albert-dpo-0912-v-5607-v2-mkmlizer: Processed model ChaiML/albert_dpo_0912_virgo_edit_variety_random in 116.088s
chaiml-albert-dpo-0912-v-5607-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-albert-dpo-0912-v-5607-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-albert-dpo-0912-v-5607-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-5607-v2
chaiml-albert-dpo-0912-v-5607-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-5607-v2/config.json
chaiml-albert-dpo-0912-v-5607-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-5607-v2/special_tokens_map.json
chaiml-albert-dpo-0912-v-5607-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-5607-v2/tokenizer_config.json
chaiml-albert-dpo-0912-v-5607-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-5607-v2/tokenizer.json
chaiml-albert-dpo-0912-v-5607-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-5607-v2/flywheel_model.0.safetensors
chaiml-albert-dpo-0912-v-5607-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 23.15it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 28.79it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:13, 25.41it/s]
Loading 0:   6%|▌         | 20/363 [00:00<00:09, 34.50it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:15, 22.57it/s]
Loading 0:   7%|▋         | 27/363 [00:01<00:15, 22.06it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:12, 25.74it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:11, 27.85it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:11, 28.74it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:11, 27.79it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 30.51it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 28.53it/s]
Loading 0:  15%|█▌        | 56/363 [00:02<00:10, 29.16it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 25.41it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:13, 22.43it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:09, 29.69it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:09, 29.22it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 28.72it/s]
Loading 0:  23%|██▎       | 84/363 [00:03<00:08, 31.38it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:09, 30.24it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:08, 32.05it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:08, 30.59it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:10, 24.89it/s]
Loading 0:  29%|██▊       | 104/363 [00:03<00:11, 22.29it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:08, 29.60it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:08, 28.30it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:07, 30.93it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:07, 30.19it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 32.69it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 31.07it/s]
Loading 0:  38%|███▊      | 137/363 [00:04<00:07, 31.13it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 26.93it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:08, 25.57it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:09, 23.55it/s]
Loading 0:  42%|████▏     | 154/363 [00:05<00:07, 28.22it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:07, 26.14it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 32.57it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 30.58it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:05, 32.71it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:05, 31.32it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 24.98it/s]
Loading 0:  51%|█████     | 185/363 [00:06<00:08, 22.24it/s]
Loading 0:  53%|█████▎    | 192/363 [00:06<00:05, 29.20it/s]
Loading 0:  54%|█████▍    | 196/363 [00:06<00:05, 28.48it/s]
Loading 0:  55%|█████▌    | 201/363 [00:07<00:05, 31.11it/s]
Loading 0:  56%|█████▋    | 205/363 [00:07<00:05, 30.06it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:04, 32.04it/s]
Loading 0:  59%|█████▉    | 214/363 [00:07<00:04, 30.37it/s]
Loading 0:  60%|██████    | 218/363 [00:07<00:04, 30.22it/s]
Loading 0:  61%|██████▏   | 223/363 [00:07<00:05, 25.51it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:05, 23.95it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:05, 23.33it/s]
Loading 0:  65%|██████▌   | 237/363 [00:08<00:04, 30.24it/s]
Loading 0:  66%|██████▋   | 241/363 [00:08<00:04, 29.19it/s]
Loading 0:  68%|██████▊   | 246/363 [00:08<00:03, 31.33it/s]
Loading 0:  69%|██████▉   | 250/363 [00:08<00:03, 29.45it/s]
Loading 0:  70%|███████   | 255/363 [00:08<00:03, 31.43it/s]
Loading 0:  71%|███████▏  | 259/363 [00:09<00:03, 28.90it/s]
Loading 0:  72%|███████▏  | 263/363 [00:09<00:04, 23.82it/s]
Loading 0:  73%|███████▎  | 266/363 [00:09<00:04, 21.48it/s]
Loading 0:  75%|███████▍  | 271/363 [00:09<00:03, 26.65it/s]
Loading 0:  76%|███████▌  | 275/363 [00:09<00:03, 25.03it/s]
Loading 0:  78%|███████▊  | 282/363 [00:10<00:02, 32.10it/s]
Loading 0:  79%|███████▉  | 286/363 [00:10<00:02, 30.90it/s]
Loading 0:  80%|████████  | 291/363 [00:10<00:02, 32.85it/s]
Loading 0:  81%|████████▏ | 295/363 [00:10<00:02, 31.42it/s]
Loading 0:  82%|████████▏ | 299/363 [00:10<00:02, 30.93it/s]
Loading 0:  84%|████████▎ | 304/363 [00:10<00:02, 25.56it/s]
Loading 0:  85%|████████▍ | 307/363 [00:10<00:02, 24.64it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 23.22it/s]
Loading 0:  87%|████████▋ | 316/363 [00:11<00:01, 28.14it/s]
Loading 0:  88%|████████▊ | 320/363 [00:11<00:01, 25.38it/s]
Loading 0:  90%|█████████ | 327/363 [00:11<00:01, 31.65it/s]
Loading 0:  91%|█████████ | 331/363 [00:11<00:01, 30.51it/s]
Loading 0:  93%|█████████▎| 336/363 [00:11<00:00, 32.74it/s]
Loading 0:  94%|█████████▎| 340/363 [00:12<00:00, 30.72it/s]
Loading 0:  95%|█████████▍| 344/363 [00:18<00:09,  2.02it/s]
Loading 0:  96%|█████████▌| 348/363 [00:19<00:05,  2.71it/s]
Loading 0:  97%|█████████▋| 353/363 [00:19<00:02,  3.91it/s]
Loading 0:  98%|█████████▊| 357/363 [00:19<00:01,  5.08it/s]
                                                            
Job chaiml-albert-dpo-0912-v-5607-v2-mkmlizer completed after 136.3s with status: succeeded
Stopping job with name chaiml-albert-dpo-0912-v-5607-v2-mkmlizer
Pipeline stage MKMLizer completed in 137.91s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-albert-dpo-0912-v-5607-v2
Waiting for inference service chaiml-albert-dpo-0912-v-5607-v2 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-5607-v2 ready after 190.992125749588s
Pipeline stage MKMLDeployer completed in 191.32s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.198042392730713s
Received healthy response to inference request in 2.5204286575317383s
Received healthy response to inference request in 1.4904098510742188s
Received healthy response to inference request in 1.3018827438354492s
Received healthy response to inference request in 1.57503080368042s
5 requests
0 failed requests
5th percentile: 1.3395881652832031
10th percentile: 1.377293586730957
20th percentile: 1.4527044296264648
30th percentile: 1.507334041595459
40th percentile: 1.5411824226379394
50th percentile: 1.57503080368042
60th percentile: 1.824235439300537
70th percentile: 2.0734400749206543
80th percentile: 2.2625196456909182
90th percentile: 2.391474151611328
95th percentile: 2.455951404571533
99th percentile: 2.5075332069396974
mean time: 1.8171588897705078
Pipeline stage StressChecker completed in 10.03s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%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
Pipeline stage TriggerMKMLProfilingPipeline completed in 7.52s
Shutdown handler de-registered
chaiml-albert-dpo-0912-v_5607_v2 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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-albert-dpo-0912-v-5607-v2-profiler
Waiting for inference service chaiml-albert-dpo-0912-v-5607-v2-profiler to be ready
Inference service chaiml-albert-dpo-0912-v-5607-v2-profiler ready after 190.43130254745483s
Pipeline stage MKMLProfilerDeployer completed in 190.80s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-albert-dpo-09db8217fe3cd225c55bd1a3b9c2f5d318-deplo2lw5c:/code/chaiverse_profiler_1726264020 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-albert-dpo-09db8217fe3cd225c55bd1a3b9c2f5d318-deplo2lw5c --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726264020 && 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_1726264020/summary.json'
kubectl exec -it chaiml-albert-dpo-09db8217fe3cd225c55bd1a3b9c2f5d318-deplo2lw5c --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726264020/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1169.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-albert-dpo-0912-v-5607-v2-profiler is running
Tearing down inference service chaiml-albert-dpo-0912-v-5607-v2-profiler
Service chaiml-albert-dpo-0912-v-5607-v2-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.98s
Shutdown handler de-registered
chaiml-albert-dpo-0912-v_5607_v2 status is now inactive due to auto deactivation removed underperforming models