submission_id: chaiml-albert-dpo-0912-v_5607_v3
developer_uid: chai_backend_admin
alignment_samples: 12432
alignment_score: -0.5998433264684015
best_of: 8
celo_rating: 1255.14
display_name: 0913-nemo-random
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_random
latencies: [{'batch_size': 1, 'throughput': 0.6111920730525656, 'latency_mean': 1.6360505151748657, 'latency_p50': 1.6390955448150635, 'latency_p90': 1.7987725734710693}, {'batch_size': 3, 'throughput': 1.0888985277087222, 'latency_mean': 2.74685533285141, 'latency_p50': 2.7516528367996216, 'latency_p90': 3.0292430639266965}, {'batch_size': 5, 'throughput': 1.2446981471507763, 'latency_mean': 4.002572085857391, 'latency_p50': 4.01083505153656, 'latency_p90': 4.461162829399109}, {'batch_size': 6, 'throughput': 1.2552010024516498, 'latency_mean': 4.759350061416626, 'latency_p50': 4.801741719245911, 'latency_p90': 5.388632225990295}, {'batch_size': 8, 'throughput': 1.2518287641950345, 'latency_mean': 6.370360888242722, 'latency_p50': 6.3653178215026855, 'latency_p90': 7.184574246406555}, {'batch_size': 10, 'throughput': 1.2090998800199482, 'latency_mean': 8.218730434179307, 'latency_p50': 8.258237481117249, 'latency_p90': 9.364051580429077}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: ChaiML/albert_dpo_0912_v
model_name: 0913-nemo-random
model_num_parameters: 12772070400.0
model_repo: ChaiML/albert_dpo_0912_virgo_edit_variety_random
model_size: 13B
num_battles: 12432
num_wins: 6305
propriety_score: 0.6946778711484594
propriety_total_count: 1071.0
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 1.22
timestamp: 2024-09-13T23:56:30+00:00
us_pacific_date: 2024-09-13
win_ratio: 0.5071589446589446
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-v3-mkmlizer
Waiting for job on chaiml-albert-dpo-0912-v-5607-v3-mkmlizer to finish
chaiml-albert-dpo-0912-v-5607-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-albert-dpo-0912-v-5607-v3-mkmlizer: ║     _____            __           __                                ║
chaiml-albert-dpo-0912-v-5607-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-albert-dpo-0912-v-5607-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-albert-dpo-0912-v-5607-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-albert-dpo-0912-v-5607-v3-mkmlizer: ║       /___/                                                         ║
chaiml-albert-dpo-0912-v-5607-v3-mkmlizer: ║                                                                     ║
chaiml-albert-dpo-0912-v-5607-v3-mkmlizer: ║  Version: 0.10.1                                                    ║
chaiml-albert-dpo-0912-v-5607-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-albert-dpo-0912-v-5607-v3-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-albert-dpo-0912-v-5607-v3-mkmlizer: ║                                                                     ║
chaiml-albert-dpo-0912-v-5607-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-albert-dpo-0912-v-5607-v3-mkmlizer: ║  belonging to:                                                      ║
chaiml-albert-dpo-0912-v-5607-v3-mkmlizer: ║                                                                     ║
chaiml-albert-dpo-0912-v-5607-v3-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-albert-dpo-0912-v-5607-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-albert-dpo-0912-v-5607-v3-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-albert-dpo-0912-v-5607-v3-mkmlizer: ║                                                                     ║
chaiml-albert-dpo-0912-v-5607-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-albert-dpo-0912-v-5607-v3-mkmlizer: Downloaded to shared memory in 58.323s
chaiml-albert-dpo-0912-v-5607-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp3cs6m8pw, device:0
chaiml-albert-dpo-0912-v-5607-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission blend_sanen_2024-09-09: ('http://zonemercy-virgo-edit-v1-1e5-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:49326->127.0.0.1:8080: read: connection reset by peer\n')
chaiml-albert-dpo-0912-v-5607-v3-mkmlizer: quantized model in 40.751s
chaiml-albert-dpo-0912-v-5607-v3-mkmlizer: Processed model ChaiML/albert_dpo_0912_virgo_edit_variety_random in 99.075s
chaiml-albert-dpo-0912-v-5607-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-albert-dpo-0912-v-5607-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-albert-dpo-0912-v-5607-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-5607-v3
chaiml-albert-dpo-0912-v-5607-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-5607-v3/tokenizer_config.json
chaiml-albert-dpo-0912-v-5607-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-5607-v3/tokenizer.json
chaiml-albert-dpo-0912-v-5607-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-5607-v3/flywheel_model.0.safetensors
chaiml-albert-dpo-0912-v-5607-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 22.39it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 28.62it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:14, 24.39it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:11, 30.30it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:15, 21.81it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:17, 19.43it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:13, 24.87it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:12, 26.40it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:11, 27.34it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:11, 26.77it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 30.01it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 28.79it/s]
Loading 0:  15%|█▌        | 56/363 [00:02<00:10, 29.14it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:09, 31.08it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:15, 19.59it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:10, 26.62it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:10, 26.46it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:10, 25.87it/s]
Loading 0:  23%|██▎       | 84/363 [00:03<00:09, 28.02it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:10, 27.44it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:09, 29.41it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:09, 28.11it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:11, 23.26it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:12, 20.95it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:08, 28.37it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:08, 27.85it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 27.07it/s]
Loading 0:  34%|███▍      | 123/363 [00:04<00:09, 25.48it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 30.25it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:07, 29.27it/s]
Loading 0:  38%|███▊      | 137/363 [00:05<00:07, 29.61it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:06, 31.93it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:09, 21.84it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:10, 21.00it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:07, 27.37it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:07, 26.40it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:06, 28.52it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:07, 27.06it/s]
Loading 0:  47%|████▋     | 172/363 [00:06<00:06, 27.49it/s]
Loading 0:  48%|████▊     | 176/363 [00:06<00:07, 25.12it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 23.72it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:08, 21.61it/s]
Loading 0:  53%|█████▎    | 192/363 [00:07<00:06, 28.45it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 27.36it/s]
Loading 0:  55%|█████▌    | 201/363 [00:07<00:05, 29.80it/s]
Loading 0:  56%|█████▋    | 205/363 [00:07<00:05, 27.98it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:05, 30.18it/s]
Loading 0:  59%|█████▉    | 214/363 [00:08<00:05, 29.30it/s]
Loading 0:  60%|██████    | 218/363 [00:08<00:05, 28.91it/s]
Loading 0:  61%|██████▏   | 223/363 [00:08<00:05, 25.14it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:05, 24.13it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:05, 23.10it/s]
Loading 0:  65%|██████▌   | 237/363 [00:08<00:04, 30.20it/s]
Loading 0:  66%|██████▋   | 241/363 [00:09<00:04, 28.65it/s]
Loading 0:  68%|██████▊   | 246/363 [00:09<00:03, 30.44it/s]
Loading 0:  69%|██████▉   | 250/363 [00:09<00:03, 29.07it/s]
Loading 0:  70%|███████   | 255/363 [00:09<00:03, 31.32it/s]
Loading 0:  71%|███████▏  | 259/363 [00:09<00:03, 29.76it/s]
Loading 0:  72%|███████▏  | 263/363 [00:09<00:04, 23.35it/s]
Loading 0:  73%|███████▎  | 266/363 [00:10<00:04, 20.97it/s]
Loading 0:  75%|███████▍  | 271/363 [00:10<00:03, 26.07it/s]
Loading 0:  76%|███████▌  | 275/363 [00:10<00:03, 24.31it/s]
Loading 0:  78%|███████▊  | 282/363 [00:10<00:02, 31.15it/s]
Loading 0:  79%|███████▉  | 286/363 [00:10<00:02, 29.56it/s]
Loading 0:  80%|████████  | 291/363 [00:10<00:02, 32.31it/s]
Loading 0:  81%|████████▏ | 295/363 [00:10<00:02, 29.88it/s]
Loading 0:  82%|████████▏ | 299/363 [00:11<00:02, 29.87it/s]
Loading 0:  84%|████████▎ | 304/363 [00:11<00:02, 24.87it/s]
Loading 0:  85%|████████▍ | 307/363 [00:11<00:02, 23.54it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 22.33it/s]
Loading 0:  88%|████████▊ | 318/363 [00:11<00:01, 28.71it/s]
Loading 0:  89%|████████▊ | 322/363 [00:12<00:01, 27.52it/s]
Loading 0:  90%|████████▉ | 325/363 [00:12<00:01, 27.96it/s]
Loading 0:  91%|█████████ | 329/363 [00:12<00:01, 24.70it/s]
Loading 0:  92%|█████████▏| 334/363 [00:12<00:00, 29.49it/s]
Loading 0:  93%|█████████▎| 338/363 [00:12<00:00, 25.69it/s]
Loading 0:  95%|█████████▍| 344/363 [00:19<00:08,  2.19it/s]
Loading 0:  96%|█████████▌| 348/363 [00:19<00:05,  2.85it/s]
Loading 0:  97%|█████████▋| 353/363 [00:19<00:02,  4.03it/s]
Loading 0:  98%|█████████▊| 357/363 [00:20<00:01,  5.15it/s]
Loading 0: 100%|█████████▉| 362/363 [00:20<00:00,  7.24it/s]
                                                            

Job chaiml-albert-dpo-0912-v-5607-v3-mkmlizer completed after 117.93s with status: succeeded
Stopping job with name chaiml-albert-dpo-0912-v-5607-v3-mkmlizer
Pipeline stage MKMLizer completed in 120.52s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-albert-dpo-0912-v-5607-v3
Waiting for inference service chaiml-albert-dpo-0912-v-5607-v3 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
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-v3 ready after 160.6901969909668s
Pipeline stage MKMLDeployer completed in 161.07s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.5471253395080566s
Received healthy response to inference request in 1.5896637439727783s
Received healthy response to inference request in 1.8544034957885742s
Received healthy response to inference request in 2.270773410797119s
Received healthy response to inference request in 0.8248734474182129s
5 requests
0 failed requests
5th percentile: 0.977831506729126
10th percentile: 1.130789566040039
20th percentile: 1.4367056846618653
30th percentile: 1.6426116943359375
40th percentile: 1.748507595062256
50th percentile: 1.8544034957885742
60th percentile: 2.0209514617919924
70th percentile: 2.18749942779541
80th percentile: 2.526043796539307
90th percentile: 3.036584568023682
95th percentile: 3.291854953765869
99th percentile: 3.496071262359619
mean time: 2.017367887496948
Pipeline stage StressChecker completed in 13.39s
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 7.78s
Shutdown handler de-registered
chaiml-albert-dpo-0912-v_5607_v3 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 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-albert-dpo-0912-v-5607-v3-profiler
Waiting for inference service chaiml-albert-dpo-0912-v-5607-v3-profiler to be ready
Inference service chaiml-albert-dpo-0912-v-5607-v3-profiler ready after 170.50209021568298s
Pipeline stage MKMLProfilerDeployer completed in 171.68s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-albert-dpo-09d487659be655c48c0fa86121b0e4b167-deplonxz7z:/code/chaiverse_profiler_1726272323 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-albert-dpo-09d487659be655c48c0fa86121b0e4b167-deplonxz7z --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726272323 && 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_1726272323/summary.json'
kubectl exec -it chaiml-albert-dpo-09d487659be655c48c0fa86121b0e4b167-deplonxz7z --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726272323/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1162.84s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-albert-dpo-0912-v-5607-v3-profiler is running
Tearing down inference service chaiml-albert-dpo-0912-v-5607-v3-profiler
Service chaiml-albert-dpo-0912-v-5607-v3-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.87s
Shutdown handler de-registered
chaiml-albert-dpo-0912-v_5607_v3 status is now inactive due to auto deactivation removed underperforming models