chaiml-albert-dpo-0912-v_2353

submission_id: chaiml-albert-dpo-0912-v_2353_v2

developer_uid: azuruce

alignment_samples: 12983

alignment_score: 2.530495562834758

best_of: 8

celo_rating: 1154.07

display_name: edit-dpo-ai-improved

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_improved

latencies: [{'batch_size': 1, 'throughput': 0.6180716303768305, 'latency_mean': 1.6178696691989898, 'latency_p50': 1.6212959289550781, 'latency_p90': 1.7784839630126952}, {'batch_size': 3, 'throughput': 1.0883270940543908, 'latency_mean': 2.7433103585243224, 'latency_p50': 2.7509946823120117, 'latency_p90': 3.0505160808563234}, {'batch_size': 5, 'throughput': 1.242281638869937, 'latency_mean': 4.010329961776733, 'latency_p50': 4.032341837882996, 'latency_p90': 4.47563145160675}, {'batch_size': 6, 'throughput': 1.2731546857563902, 'latency_mean': 4.684474660158157, 'latency_p50': 4.736502647399902, 'latency_p90': 5.241850566864014}, {'batch_size': 8, 'throughput': 1.2397449209596936, 'latency_mean': 6.415907999277115, 'latency_p50': 6.401788234710693, 'latency_p90': 7.318530511856079}, {'batch_size': 10, 'throughput': 1.223454807192422, 'latency_mean': 8.124819712638855, 'latency_p50': 8.1539808511734, 'latency_p90': 9.292541790008546}]

max_input_tokens: 1024

max_output_tokens: 64

model_architecture: MistralForCausalLM

model_group: ChaiML/albert_dpo_0912_v

model_name: edit-dpo-ai-improved

model_num_parameters: 12772070400.0

model_repo: ChaiML/albert_dpo_0912_virgo_edit_improved

model_size: 13B

num_battles: 12983

num_wins: 4768

propriety_score: 0.7522935779816514

propriety_total_count: 1090.0

ranking_group: single

status: inactive

submission_type: basic

throughput_3p7s: 1.22

timestamp: 2024-09-15T05:22:48+00:00

us_pacific_date: 2024-09-14

win_ratio: 0.3672494800893476

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-2353-v2-mkmlizer
Waiting for job on chaiml-albert-dpo-0912-v-2353-v2-mkmlizer to finish
chaiml-albert-dpo-0912-v-2353-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-albert-dpo-0912-v-2353-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-albert-dpo-0912-v-2353-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-albert-dpo-0912-v-2353-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-albert-dpo-0912-v-2353-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-albert-dpo-0912-v-2353-v2-mkmlizer: ║       /___/                                                         ║
chaiml-albert-dpo-0912-v-2353-v2-mkmlizer: ║                                                                     ║
chaiml-albert-dpo-0912-v-2353-v2-mkmlizer: ║  Version: 0.10.1                                                    ║
chaiml-albert-dpo-0912-v-2353-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-albert-dpo-0912-v-2353-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-albert-dpo-0912-v-2353-v2-mkmlizer: ║                                                                     ║
chaiml-albert-dpo-0912-v-2353-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-albert-dpo-0912-v-2353-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-albert-dpo-0912-v-2353-v2-mkmlizer: ║                                                                     ║
chaiml-albert-dpo-0912-v-2353-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-albert-dpo-0912-v-2353-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-albert-dpo-0912-v-2353-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-albert-dpo-0912-v-2353-v2-mkmlizer: ║                                                                     ║
chaiml-albert-dpo-0912-v-2353-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission blend_hokok_2024-09-09: ('http://neversleep-noromaid-v0-8068-v150-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-albert-dpo-0912-v-2353-v2-mkmlizer: Downloaded to shared memory in 69.691s
chaiml-albert-dpo-0912-v-2353-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp5shjlma4, device:0
chaiml-albert-dpo-0912-v-2353-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-albert-dpo-0912-v-2353-v2-mkmlizer: quantized model in 40.009s
chaiml-albert-dpo-0912-v-2353-v2-mkmlizer: Processed model ChaiML/albert_dpo_0912_virgo_edit_improved in 109.701s
chaiml-albert-dpo-0912-v-2353-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-albert-dpo-0912-v-2353-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-albert-dpo-0912-v-2353-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-2353-v2
chaiml-albert-dpo-0912-v-2353-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-2353-v2/config.json
chaiml-albert-dpo-0912-v-2353-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-2353-v2/special_tokens_map.json
chaiml-albert-dpo-0912-v-2353-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-2353-v2/tokenizer_config.json
chaiml-albert-dpo-0912-v-2353-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-2353-v2/tokenizer.json
chaiml-albert-dpo-0912-v-2353-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-2353-v2/flywheel_model.0.safetensors
chaiml-albert-dpo-0912-v-2353-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 23.75it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:11, 30.45it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:13, 25.98it/s]
Loading 0:   6%|▌         | 20/363 [00:00<00:09, 34.91it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:13, 25.88it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:13, 25.62it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:13, 24.47it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:10, 31.48it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:10, 30.25it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 33.02it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 29.27it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:10, 28.63it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 25.20it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:13, 22.20it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:09, 29.22it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:10, 28.66it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 27.32it/s]
Loading 0:  23%|██▎       | 84/363 [00:02<00:09, 29.34it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:09, 27.95it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:08, 30.23it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:09, 28.52it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:10, 23.85it/s]
Loading 0:  29%|██▊       | 104/363 [00:03<00:12, 21.44it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:08, 28.66it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:08, 28.52it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:07, 31.91it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:07, 30.28it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 30.81it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 29.80it/s]
Loading 0:  38%|███▊      | 137/363 [00:04<00:07, 30.64it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 27.64it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:08, 25.39it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:09, 23.72it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:06, 30.17it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:06, 29.26it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 32.16it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 30.73it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:05, 33.31it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:05, 31.05it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 25.66it/s]
Loading 0:  51%|█████     | 185/363 [00:06<00:07, 22.45it/s]
Loading 0:  53%|█████▎    | 192/363 [00:06<00:05, 29.52it/s]
Loading 0:  54%|█████▍    | 196/363 [00:06<00:05, 28.75it/s]
Loading 0:  55%|█████▌    | 201/363 [00:07<00:05, 31.04it/s]
Loading 0:  56%|█████▋    | 205/363 [00:07<00:05, 29.87it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:04, 32.48it/s]
Loading 0:  59%|█████▉    | 214/363 [00:07<00:04, 30.94it/s]
Loading 0:  60%|██████    | 218/363 [00:07<00:04, 31.49it/s]
Loading 0:  61%|██████▏   | 223/363 [00:07<00:05, 27.65it/s]
Loading 0:  62%|██████▏   | 226/363 [00:07<00:05, 25.50it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:05, 23.71it/s]
Loading 0:  65%|██████▌   | 237/363 [00:08<00:04, 30.17it/s]
Loading 0:  66%|██████▋   | 241/363 [00:08<00:04, 28.07it/s]
Loading 0:  68%|██████▊   | 246/363 [00:08<00:03, 29.65it/s]
Loading 0:  69%|██████▉   | 250/363 [00:08<00:04, 28.13it/s]
Loading 0:  70%|███████   | 255/363 [00:08<00:03, 29.82it/s]
Loading 0:  71%|███████▏  | 259/363 [00:09<00:03, 28.38it/s]
Loading 0:  72%|███████▏  | 263/363 [00:09<00:04, 24.34it/s]
Loading 0:  73%|███████▎  | 266/363 [00:09<00:04, 21.78it/s]
Loading 0:  75%|███████▌  | 273/363 [00:09<00:03, 28.99it/s]
Loading 0:  76%|███████▋  | 277/363 [00:09<00:03, 28.31it/s]
Loading 0:  78%|███████▊  | 282/363 [00:09<00:02, 30.61it/s]
Loading 0:  79%|███████▉  | 286/363 [00:10<00:02, 28.85it/s]
Loading 0:  80%|████████  | 291/363 [00:10<00:02, 30.74it/s]
Loading 0:  81%|████████▏ | 295/363 [00:10<00:02, 29.62it/s]
Loading 0:  82%|████████▏ | 299/363 [00:10<00:02, 30.31it/s]
Loading 0:  84%|████████▎ | 304/363 [00:10<00:02, 26.35it/s]
Loading 0:  85%|████████▍ | 307/363 [00:10<00:02, 24.88it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 23.86it/s]
Loading 0:  88%|████████▊ | 318/363 [00:11<00:01, 30.59it/s]
Loading 0:  89%|████████▊ | 322/363 [00:11<00:01, 29.42it/s]
Loading 0:  90%|█████████ | 327/363 [00:11<00:01, 32.05it/s]
Loading 0:  91%|█████████ | 331/363 [00:11<00:01, 30.31it/s]
Loading 0:  93%|█████████▎| 336/363 [00:11<00:00, 32.85it/s]
Loading 0:  94%|█████████▎| 340/363 [00:11<00:00, 30.93it/s]
Loading 0:  95%|█████████▍| 344/363 [00:18<00:09,  1.99it/s]
Loading 0:  96%|█████████▌| 348/363 [00:19<00:05,  2.67it/s]
Loading 0:  97%|█████████▋| 353/363 [00:19<00:02,  3.88it/s]
Loading 0:  98%|█████████▊| 357/363 [00:19<00:01,  5.04it/s]
                                                            
Job chaiml-albert-dpo-0912-v-2353-v2-mkmlizer completed after 136.59s with status: succeeded
Stopping job with name chaiml-albert-dpo-0912-v-2353-v2-mkmlizer
Pipeline stage MKMLizer completed in 137.67s
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-2353-v2
Waiting for inference service chaiml-albert-dpo-0912-v-2353-v2 to be ready
Failed to get response for submission blend_hokok_2024-09-09: ('http://neversleep-noromaid-v0-8068-v150-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
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
Failed to get response for submission blend_hokok_2024-09-09: ('http://neversleep-noromaid-v0-8068-v150-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Failed to get response for submission blend_hokok_2024-09-09: ('http://neversleep-noromaid-v0-8068-v150-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Inference service chaiml-albert-dpo-0912-v-2353-v2 ready after 160.67720246315002s
Pipeline stage MKMLDeployer completed in 161.07s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.9048452377319336s
Received healthy response to inference request in 2.044779062271118s
Received healthy response to inference request in 1.117690086364746s
Received healthy response to inference request in 1.161142110824585s
Received healthy response to inference request in 1.2817420959472656s
5 requests
0 failed requests
5th percentile: 1.126380491256714
10th percentile: 1.1350708961486817
20th percentile: 1.1524517059326171
30th percentile: 1.185262107849121
40th percentile: 1.2335021018981933
50th percentile: 1.2817420959472656
60th percentile: 1.5869568824768066
70th percentile: 1.8921716690063475
80th percentile: 2.2167922973632814
90th percentile: 2.5608187675476075
95th percentile: 2.7328320026397703
99th percentile: 2.870442590713501
mean time: 1.7020397186279297
Pipeline stage StressChecker completed in 9.49s
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 5.33s
Shutdown handler de-registered
chaiml-albert-dpo-0912-v_2353_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 0.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-albert-dpo-0912-v-2353-v2-profiler
Waiting for inference service chaiml-albert-dpo-0912-v-2353-v2-profiler to be ready
Inference service chaiml-albert-dpo-0912-v-2353-v2-profiler ready after 170.40015411376953s
Pipeline stage MKMLProfilerDeployer completed in 173.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-albert-dpo-0996098f8cd72bed8247a7c464cae7c6c9-deploq5fk7:/code/chaiverse_profiler_1726378297 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-albert-dpo-0996098f8cd72bed8247a7c464cae7c6c9-deploq5fk7 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726378297 && 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_1726378297/summary.json'
kubectl exec -it chaiml-albert-dpo-0996098f8cd72bed8247a7c464cae7c6c9-deploq5fk7 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726378297/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1160.02s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-albert-dpo-0912-v-2353-v2-profiler is running
Tearing down inference service chaiml-albert-dpo-0912-v-2353-v2-profiler
Service chaiml-albert-dpo-0912-v-2353-v2-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.99s
Shutdown handler de-registered
chaiml-albert-dpo-0912-v_2353_v2 status is now inactive due to auto deactivation removed underperforming models