chaiml-albert-dpo-0912-v_8296

submission_id: chaiml-albert-dpo-0912-v_8296_v6

developer_uid: azuruce

alignment_samples: 11937

alignment_score: 0.3623560078595241

best_of: 8

celo_rating: 1248.03

display_name: 0821v1-0

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_ai_selected

latencies: [{'batch_size': 1, 'throughput': 0.6107871510555349, 'latency_mean': 1.6371339893341064, 'latency_p50': 1.6223613023757935, 'latency_p90': 1.812048602104187}, {'batch_size': 3, 'throughput': 1.068754259434461, 'latency_mean': 2.7971387100219727, 'latency_p50': 2.794050097465515, 'latency_p90': 3.1073102712631226}, {'batch_size': 5, 'throughput': 1.211100402732152, 'latency_mean': 4.118222748041153, 'latency_p50': 4.14024019241333, 'latency_p90': 4.631346392631531}, {'batch_size': 6, 'throughput': 1.2450609168767617, 'latency_mean': 4.798904522657394, 'latency_p50': 4.816505432128906, 'latency_p90': 5.37389919757843}, {'batch_size': 8, 'throughput': 1.218956373751959, 'latency_mean': 6.522393387556076, 'latency_p50': 6.545689105987549, 'latency_p90': 7.385479807853699}, {'batch_size': 10, 'throughput': 1.191266777420696, 'latency_mean': 8.347058801651, 'latency_p50': 8.36039137840271, 'latency_p90': 9.38462917804718}]

max_input_tokens: 1024

max_output_tokens: 64

model_architecture: MistralForCausalLM

model_group: ChaiML/albert_dpo_0912_v

model_name: 0821v1-0

model_num_parameters: 12772070400.0

model_repo: ChaiML/albert_dpo_0912_virgo_edit_ai_selected

model_size: 13B

num_battles: 11937

num_wins: 6000

propriety_score: 0.7217777777777777

propriety_total_count: 1125.0

ranking_group: single

status: inactive

submission_type: basic

throughput_3p7s: 1.18

timestamp: 2024-09-15T05:32:56+00:00

us_pacific_date: 2024-09-14

win_ratio: 0.5026388539834129

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-8296-v6-mkmlizer
Waiting for job on chaiml-albert-dpo-0912-v-8296-v6-mkmlizer to finish
chaiml-albert-dpo-0912-v-8296-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-albert-dpo-0912-v-8296-v6-mkmlizer: ║     _____            __           __                                ║
chaiml-albert-dpo-0912-v-8296-v6-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-albert-dpo-0912-v-8296-v6-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-albert-dpo-0912-v-8296-v6-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-albert-dpo-0912-v-8296-v6-mkmlizer: ║       /___/                                                         ║
chaiml-albert-dpo-0912-v-8296-v6-mkmlizer: ║                                                                     ║
chaiml-albert-dpo-0912-v-8296-v6-mkmlizer: ║  Version: 0.10.1                                                    ║
chaiml-albert-dpo-0912-v-8296-v6-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-albert-dpo-0912-v-8296-v6-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-albert-dpo-0912-v-8296-v6-mkmlizer: ║                                                                     ║
chaiml-albert-dpo-0912-v-8296-v6-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-albert-dpo-0912-v-8296-v6-mkmlizer: ║  belonging to:                                                      ║
chaiml-albert-dpo-0912-v-8296-v6-mkmlizer: ║                                                                     ║
chaiml-albert-dpo-0912-v-8296-v6-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-albert-dpo-0912-v-8296-v6-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-albert-dpo-0912-v-8296-v6-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-albert-dpo-0912-v-8296-v6-mkmlizer: ║                                                                     ║
chaiml-albert-dpo-0912-v-8296-v6-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', '')
chaiml-albert-dpo-0912-v-8296-v6-mkmlizer: Downloaded to shared memory in 54.684s
chaiml-albert-dpo-0912-v-8296-v6-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpaa8kcvps, device:0
chaiml-albert-dpo-0912-v-8296-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-albert-dpo-0912-v-8296-v6-mkmlizer: quantized model in 40.058s
chaiml-albert-dpo-0912-v-8296-v6-mkmlizer: Processed model ChaiML/albert_dpo_0912_virgo_edit_ai_selected in 94.742s
chaiml-albert-dpo-0912-v-8296-v6-mkmlizer: creating bucket guanaco-mkml-models
chaiml-albert-dpo-0912-v-8296-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-albert-dpo-0912-v-8296-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-8296-v6
chaiml-albert-dpo-0912-v-8296-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-8296-v6/config.json
chaiml-albert-dpo-0912-v-8296-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-8296-v6/special_tokens_map.json
chaiml-albert-dpo-0912-v-8296-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-8296-v6/tokenizer_config.json
chaiml-albert-dpo-0912-v-8296-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-8296-v6/flywheel_model.0.safetensors
chaiml-albert-dpo-0912-v-8296-v6-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 22.62it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 28.87it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:13, 25.81it/s]
Loading 0:   6%|▌         | 20/363 [00:00<00:09, 34.38it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:15, 22.13it/s]
Loading 0:   7%|▋         | 27/363 [00:01<00:15, 21.92it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:13, 25.52it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:11, 27.52it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:11, 29.36it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:11, 28.72it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 30.96it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 29.78it/s]
Loading 0:  15%|█▌        | 56/363 [00:02<00:10, 29.98it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:12, 24.56it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:13, 21.82it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:10, 28.86it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:10, 28.71it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 27.64it/s]
Loading 0:  23%|██▎       | 84/363 [00:03<00:09, 30.44it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:09, 29.59it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:08, 30.68it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:08, 29.78it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:10, 24.11it/s]
Loading 0:  29%|██▊       | 104/363 [00:03<00:12, 21.55it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:09, 26.82it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:10, 24.97it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:07, 31.40it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 29.83it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 31.85it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 30.16it/s]
Loading 0:  38%|███▊      | 137/363 [00:04<00:07, 30.64it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 26.33it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:08, 25.15it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:08, 24.02it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:06, 29.82it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:06, 29.15it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 31.69it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:06, 30.44it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:05, 32.25it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 30.65it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 24.92it/s]
Loading 0:  51%|█████     | 185/363 [00:06<00:08, 22.21it/s]
Loading 0:  53%|█████▎    | 192/363 [00:06<00:05, 29.15it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 27.59it/s]
Loading 0:  55%|█████▌    | 201/363 [00:07<00:05, 29.81it/s]
Loading 0:  56%|█████▋    | 205/363 [00:07<00:05, 28.98it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:04, 30.86it/s]
Loading 0:  59%|█████▉    | 214/363 [00:07<00:05, 29.75it/s]
Loading 0:  60%|██████    | 218/363 [00:07<00:04, 30.29it/s]
Loading 0:  61%|██████▏   | 223/363 [00:08<00:05, 26.20it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:05, 25.03it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:05, 23.49it/s]
Loading 0:  65%|██████▍   | 235/363 [00:08<00:04, 28.42it/s]
Loading 0:  66%|██████▌   | 239/363 [00:08<00:04, 25.55it/s]
Loading 0:  68%|██████▊   | 246/363 [00:08<00:03, 32.37it/s]
Loading 0:  69%|██████▉   | 250/363 [00:08<00:03, 30.74it/s]
Loading 0:  70%|███████   | 255/363 [00:09<00:03, 32.16it/s]
Loading 0:  71%|███████▏  | 259/363 [00:09<00:03, 30.92it/s]
Loading 0:  72%|███████▏  | 263/363 [00:09<00:04, 24.46it/s]
Loading 0:  73%|███████▎  | 266/363 [00:09<00:04, 22.24it/s]
Loading 0:  75%|███████▍  | 271/363 [00:09<00:03, 27.51it/s]
Loading 0:  76%|███████▌  | 275/363 [00:09<00:03, 25.42it/s]
Loading 0:  78%|███████▊  | 282/363 [00:10<00:02, 32.14it/s]
Loading 0:  79%|███████▉  | 286/363 [00:10<00:02, 30.85it/s]
Loading 0:  80%|████████  | 291/363 [00:10<00:02, 33.12it/s]
Loading 0:  81%|████████▏ | 295/363 [00:10<00:02, 31.34it/s]
Loading 0:  82%|████████▏ | 299/363 [00:10<00:02, 31.32it/s]
Loading 0:  84%|████████▎ | 304/363 [00:10<00:02, 26.26it/s]
Loading 0:  85%|████████▍ | 307/363 [00:11<00:02, 24.97it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 23.84it/s]
Loading 0:  87%|████████▋ | 316/363 [00:11<00:01, 29.03it/s]
Loading 0:  88%|████████▊ | 320/363 [00:11<00:01, 26.30it/s]
Loading 0:  90%|█████████ | 327/363 [00:11<00:01, 32.99it/s]
Loading 0:  91%|█████████ | 331/363 [00:11<00:01, 31.25it/s]
Loading 0:  93%|█████████▎| 336/363 [00:11<00:00, 33.44it/s]
Loading 0:  94%|█████████▎| 340/363 [00:12<00:00, 31.83it/s]
Loading 0:  95%|█████████▍| 344/363 [00:18<00:09,  2.03it/s]
Loading 0:  96%|█████████▌| 348/363 [00:19<00:05,  2.71it/s]
Loading 0:  97%|█████████▋| 353/363 [00:19<00:02,  3.92it/s]
Loading 0:  98%|█████████▊| 357/363 [00:19<00:01,  5.07it/s]
                                                            
Job chaiml-albert-dpo-0912-v-8296-v6-mkmlizer completed after 114.74s with status: succeeded
Stopping job with name chaiml-albert-dpo-0912-v-8296-v6-mkmlizer
Pipeline stage MKMLizer completed in 117.10s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.07s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-albert-dpo-0912-v-8296-v6
Waiting for inference service chaiml-albert-dpo-0912-v-8296-v6 to be ready
Inference service chaiml-albert-dpo-0912-v-8296-v6 ready after 170.7116403579712s
Pipeline stage MKMLDeployer completed in 171.04s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9926977157592773s
Received healthy response to inference request in 2.1664178371429443s
Received healthy response to inference request in 1.853419542312622s
Received healthy response to inference request in 1.6652657985687256s
Received healthy response to inference request in 4.279690265655518s
5 requests
0 failed requests
5th percentile: 1.7028965473175048
10th percentile: 1.740527296066284
20th percentile: 1.8157887935638428
30th percentile: 1.8812751770019531
40th percentile: 1.9369864463806152
50th percentile: 1.9926977157592773
60th percentile: 2.062185764312744
70th percentile: 2.131673812866211
80th percentile: 2.5890723228454595
90th percentile: 3.4343812942504885
95th percentile: 3.8570357799530024
99th percentile: 4.195159368515014
mean time: 2.3914982318878173
Pipeline stage StressChecker completed in 16.11s
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 6.32s
Shutdown handler de-registered
chaiml-albert-dpo-0912-v_8296_v6 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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-albert-dpo-0912-v-8296-v6-profiler
Waiting for inference service chaiml-albert-dpo-0912-v-8296-v6-profiler to be ready
Inference service chaiml-albert-dpo-0912-v-8296-v6-profiler ready after 170.40344190597534s
Pipeline stage MKMLProfilerDeployer completed in 177.36s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-albert-dpo-092ea1d489fd6485d06363e7114d6713e0-deplo782k8:/code/chaiverse_profiler_1726378911 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-albert-dpo-092ea1d489fd6485d06363e7114d6713e0-deplo782k8 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726378911 && 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_1726378911/summary.json'
kubectl exec -it chaiml-albert-dpo-092ea1d489fd6485d06363e7114d6713e0-deplo782k8 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726378911/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1187.50s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-albert-dpo-0912-v-8296-v6-profiler is running
Tearing down inference service chaiml-albert-dpo-0912-v-8296-v6-profiler
Service chaiml-albert-dpo-0912-v-8296-v6-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 9.30s
Shutdown handler de-registered
chaiml-albert-dpo-0912-v_8296_v6 status is now inactive due to auto deactivation removed underperforming models