chaiml-albert-dpo-0912-v_9673

submission_id: chaiml-albert-dpo-0912-v_9673_v2

developer_uid: chai_backend_admin

alignment_samples: 12035

alignment_score: -0.2252719178653691

best_of: 8

celo_rating: 1245.53

display_name: 0913-nemo-ai-disagree-with-user

formatter: {'memory_template': 'Bot Name: {bot_name}\n####\n', '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_ai_disagree_with_user

latencies: [{'batch_size': 1, 'throughput': 0.6150179742948261, 'latency_mean': 1.6259125447273255, 'latency_p50': 1.6244816780090332, 'latency_p90': 1.7905940294265748}, {'batch_size': 3, 'throughput': 1.0741691432657585, 'latency_mean': 2.7808770859241485, 'latency_p50': 2.8093862533569336, 'latency_p90': 3.0929482221603393}, {'batch_size': 5, 'throughput': 1.2286311160142913, 'latency_mean': 4.060438684225082, 'latency_p50': 4.068119168281555, 'latency_p90': 4.607110500335693}, {'batch_size': 6, 'throughput': 1.2419189183200037, 'latency_mean': 4.813340059518814, 'latency_p50': 4.795956015586853, 'latency_p90': 5.358851218223571}, {'batch_size': 8, 'throughput': 1.2272762687963623, 'latency_mean': 6.470800859928131, 'latency_p50': 6.515128970146179, 'latency_p90': 7.1186569929122925}, {'batch_size': 10, 'throughput': 1.1959045695010113, 'latency_mean': 8.315357888936996, 'latency_p50': 8.312466740608215, 'latency_p90': 9.399073815345764}]

max_input_tokens: 1024

max_output_tokens: 64

model_architecture: MistralForCausalLM

model_group: ChaiML/albert_dpo_0912_v

model_name: 0913-nemo-ai-disagree-with-user

model_num_parameters: 12772070400.0

model_repo: ChaiML/albert_dpo_0912_virgo_edit_variety_ai_disagree_with_user

model_size: 13B

num_battles: 12035

num_wins: 5932

propriety_score: 0.708498023715415

propriety_total_count: 1012.0

ranking_group: single

status: inactive

submission_type: basic

throughput_3p7s: 1.2

timestamp: 2024-09-13T23:57:22+00:00

us_pacific_date: 2024-09-13

win_ratio: 0.49289572081429167

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-9673-v2-mkmlizer
Waiting for job on chaiml-albert-dpo-0912-v-9673-v2-mkmlizer to finish
chaiml-albert-dpo-0912-v-9673-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-albert-dpo-0912-v-9673-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-albert-dpo-0912-v-9673-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-albert-dpo-0912-v-9673-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-albert-dpo-0912-v-9673-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-albert-dpo-0912-v-9673-v2-mkmlizer: ║       /___/                                                         ║
chaiml-albert-dpo-0912-v-9673-v2-mkmlizer: ║                                                                     ║
chaiml-albert-dpo-0912-v-9673-v2-mkmlizer: ║  Version: 0.10.1                                                    ║
chaiml-albert-dpo-0912-v-9673-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-albert-dpo-0912-v-9673-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-albert-dpo-0912-v-9673-v2-mkmlizer: ║                                                                     ║
chaiml-albert-dpo-0912-v-9673-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-albert-dpo-0912-v-9673-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-albert-dpo-0912-v-9673-v2-mkmlizer: ║                                                                     ║
chaiml-albert-dpo-0912-v-9673-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-albert-dpo-0912-v-9673-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-albert-dpo-0912-v-9673-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-albert-dpo-0912-v-9673-v2-mkmlizer: ║                                                                     ║
chaiml-albert-dpo-0912-v-9673-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-albert-dpo-0912-v-9673-v2-mkmlizer: Downloaded to shared memory in 60.732s
chaiml-albert-dpo-0912-v-9673-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpia419o1s, device:0
chaiml-albert-dpo-0912-v-9673-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-albert-dpo-0912-v-9673-v2-mkmlizer: quantized model in 40.879s
chaiml-albert-dpo-0912-v-9673-v2-mkmlizer: Processed model ChaiML/albert_dpo_0912_virgo_edit_variety_ai_disagree_with_user in 101.612s
chaiml-albert-dpo-0912-v-9673-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-albert-dpo-0912-v-9673-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-albert-dpo-0912-v-9673-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-9673-v2
chaiml-albert-dpo-0912-v-9673-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-9673-v2/config.json
chaiml-albert-dpo-0912-v-9673-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-9673-v2/special_tokens_map.json
chaiml-albert-dpo-0912-v-9673-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-9673-v2/tokenizer_config.json
chaiml-albert-dpo-0912-v-9673-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-9673-v2/tokenizer.json
chaiml-albert-dpo-0912-v-9673-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-9673-v2/flywheel_model.0.safetensors
chaiml-albert-dpo-0912-v-9673-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:14, 24.00it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:11, 29.97it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:13, 25.94it/s]
Loading 0:   6%|▌         | 20/363 [00:00<00:09, 35.06it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:15, 22.48it/s]
Loading 0:   7%|▋         | 27/363 [00:01<00:15, 21.84it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:13, 25.37it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:12, 27.29it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:11, 29.00it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:11, 27.90it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 30.77it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 27.98it/s]
Loading 0:  15%|█▌        | 56/363 [00:02<00:10, 28.51it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:12, 24.70it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:13, 21.93it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:10, 27.28it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:10, 27.24it/s]
Loading 0:  21%|██        | 77/363 [00:02<00:11, 24.93it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:09, 29.81it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 26.35it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:08, 32.54it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:08, 30.17it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:11, 23.24it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:12, 21.23it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:09, 27.76it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:09, 27.31it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 30.03it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 29.10it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 31.94it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 29.47it/s]
Loading 0:  38%|███▊      | 137/363 [00:05<00:07, 29.32it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 26.46it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:08, 25.05it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:08, 23.81it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:06, 30.72it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:06, 29.55it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 32.18it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:06, 31.04it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:05, 33.29it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:05, 31.84it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 24.30it/s]
Loading 0:  51%|█████     | 185/363 [00:06<00:08, 21.71it/s]
Loading 0:  53%|█████▎    | 192/363 [00:06<00:06, 28.29it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:05, 27.89it/s]
Loading 0:  55%|█████▌    | 201/363 [00:07<00:05, 29.89it/s]
Loading 0:  56%|█████▋    | 205/363 [00:07<00:05, 28.87it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:04, 30.77it/s]
Loading 0:  59%|█████▉    | 214/363 [00:07<00:05, 29.08it/s]
Loading 0:  60%|██████    | 218/363 [00:07<00:05, 28.96it/s]
Loading 0:  61%|██████▏   | 223/363 [00:08<00:05, 24.31it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:05, 23.59it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:05, 22.85it/s]
Loading 0:  65%|██████▍   | 235/363 [00:08<00:04, 28.08it/s]
Loading 0:  66%|██████▌   | 239/363 [00:08<00:04, 25.56it/s]
Loading 0:  68%|██████▊   | 246/363 [00:08<00:03, 31.86it/s]
Loading 0:  69%|██████▉   | 250/363 [00:09<00:03, 30.00it/s]
Loading 0:  70%|███████   | 255/363 [00:09<00:03, 31.78it/s]
Loading 0:  71%|███████▏  | 259/363 [00:09<00:03, 29.57it/s]
Loading 0:  72%|███████▏  | 263/363 [00:09<00:04, 24.20it/s]
Loading 0:  73%|███████▎  | 266/363 [00:09<00:04, 21.93it/s]
Loading 0:  75%|███████▌  | 273/363 [00:09<00:03, 29.10it/s]
Loading 0:  76%|███████▋  | 277/363 [00:10<00:03, 28.54it/s]
Loading 0:  78%|███████▊  | 282/363 [00:10<00:02, 31.33it/s]
Loading 0:  79%|███████▉  | 286/363 [00:10<00:02, 29.67it/s]
Loading 0:  80%|████████  | 291/363 [00:10<00:02, 31.79it/s]
Loading 0:  81%|████████▏ | 295/363 [00:10<00:02, 30.54it/s]
Loading 0:  82%|████████▏ | 299/363 [00:10<00:02, 30.89it/s]
Loading 0:  84%|████████▎ | 304/363 [00:10<00:02, 26.84it/s]
Loading 0:  85%|████████▍ | 307/363 [00:11<00:02, 25.18it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 23.66it/s]
Loading 0:  88%|████████▊ | 318/363 [00:11<00:01, 30.19it/s]
Loading 0:  89%|████████▊ | 322/363 [00:11<00:01, 29.21it/s]
Loading 0:  90%|█████████ | 327/363 [00:11<00:01, 31.63it/s]
Loading 0:  91%|█████████ | 331/363 [00:11<00:01, 29.83it/s]
Loading 0:  92%|█████████▏| 335/363 [00:12<00:00, 30.80it/s]
Loading 0:  93%|█████████▎| 339/363 [00:12<00:00, 27.41it/s]
Loading 0:  95%|█████████▍| 344/363 [00:19<00:09,  2.06it/s]
Loading 0:  96%|█████████▌| 348/363 [00:19<00:05,  2.76it/s]
Loading 0:  97%|█████████▋| 353/363 [00:19<00:02,  3.97it/s]
Loading 0:  98%|█████████▊| 357/363 [00:19<00:01,  5.12it/s]
                                                            
Job chaiml-albert-dpo-0912-v-9673-v2-mkmlizer completed after 124.51s with status: succeeded
Stopping job with name chaiml-albert-dpo-0912-v-9673-v2-mkmlizer
Pipeline stage MKMLizer completed in 125.30s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-albert-dpo-0912-v-9673-v2
Waiting for inference service chaiml-albert-dpo-0912-v-9673-v2 to be ready
Inference service chaiml-albert-dpo-0912-v-9673-v2 ready after 171.6497519016266s
Pipeline stage MKMLDeployer completed in 172.97s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2791802883148193s
Received healthy response to inference request in 1.7613246440887451s
Received healthy response to inference request in 4.164265394210815s
Received healthy response to inference request in 2.388885259628296s
Received healthy response to inference request in 1.3615751266479492s
5 requests
0 failed requests
5th percentile: 1.4415250301361084
10th percentile: 1.5214749336242677
20th percentile: 1.681374740600586
30th percentile: 1.86489577293396
40th percentile: 2.0720380306243897
50th percentile: 2.2791802883148193
60th percentile: 2.32306227684021
70th percentile: 2.3669442653656008
80th percentile: 2.7439612865448
90th percentile: 3.4541133403778077
95th percentile: 3.8091893672943113
99th percentile: 4.093250188827515
mean time: 2.391046142578125
Pipeline stage StressChecker completed in 16.40s
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 4.85s
Shutdown handler de-registered
chaiml-albert-dpo-0912-v_9673_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 0.13s
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-albert-dpo-0912-v-9673-v2-profiler
Waiting for inference service chaiml-albert-dpo-0912-v-9673-v2-profiler to be ready
Inference service chaiml-albert-dpo-0912-v-9673-v2-profiler ready after 170.38432550430298s
Pipeline stage MKMLProfilerDeployer completed in 170.75s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-albert-dpo-09715081b3f6de2f723271bbd61ad36e90-deplo5hfcm:/code/chaiverse_profiler_1726272375 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-albert-dpo-09715081b3f6de2f723271bbd61ad36e90-deplo5hfcm --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726272375 && 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_1726272375/summary.json'
kubectl exec -it chaiml-albert-dpo-09715081b3f6de2f723271bbd61ad36e90-deplo5hfcm --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726272375/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1172.60s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-albert-dpo-0912-v-9673-v2-profiler is running
Tearing down inference service chaiml-albert-dpo-0912-v-9673-v2-profiler
Service chaiml-albert-dpo-0912-v-9673-v2-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 3.48s
Shutdown handler de-registered
chaiml-albert-dpo-0912-v_9673_v2 status is now inactive due to auto deactivation removed underperforming models