chaiml-albert-dpo-0912-v_2353

submission_id: chaiml-albert-dpo-0912-v_2353_v3

developer_uid: azuruce

alignment_samples: 11633

alignment_score: 2.69247679531698

best_of: 8

celo_rating: 1125.11

display_name: ai-improved

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_improved

latencies: [{'batch_size': 1, 'throughput': 0.6245591766981019, 'latency_mean': 1.601034265756607, 'latency_p50': 1.588258981704712, 'latency_p90': 1.7865989446640014}, {'batch_size': 3, 'throughput': 1.0786275990435643, 'latency_mean': 2.7714994561672213, 'latency_p50': 2.759498953819275, 'latency_p90': 3.0362457275390624}, {'batch_size': 5, 'throughput': 1.2466576081194531, 'latency_mean': 4.0014718770980835, 'latency_p50': 3.999752998352051, 'latency_p90': 4.505278944969177}, {'batch_size': 6, 'throughput': 1.2630663556108874, 'latency_mean': 4.728247499465942, 'latency_p50': 4.783358216285706, 'latency_p90': 5.305705213546753}, {'batch_size': 8, 'throughput': 1.250182275227513, 'latency_mean': 6.35460626244545, 'latency_p50': 6.397478699684143, 'latency_p90': 7.209334754943848}, {'batch_size': 10, 'throughput': 1.2225470170430668, 'latency_mean': 8.139923516511917, 'latency_p50': 8.213266134262085, 'latency_p90': 9.15675799846649}]

max_input_tokens: 1024

max_output_tokens: 64

model_architecture: MistralForCausalLM

model_group: ChaiML/albert_dpo_0912_v

model_name: ai-improved

model_num_parameters: 12772070400.0

model_repo: ChaiML/albert_dpo_0912_virgo_edit_improved

model_size: 13B

num_battles: 11632

num_wins: 3826

propriety_score: 0.7476635514018691

propriety_total_count: 1070.0

ranking_group: single

status: inactive

submission_type: basic

throughput_3p7s: 1.22

timestamp: 2024-09-15T05:33:33+00:00

us_pacific_date: 2024-09-14

win_ratio: 0.32892022008253097

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-v3-mkmlizer
Waiting for job on chaiml-albert-dpo-0912-v-2353-v3-mkmlizer to finish
chaiml-albert-dpo-0912-v-2353-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-albert-dpo-0912-v-2353-v3-mkmlizer: ║     _____            __           __                                ║
chaiml-albert-dpo-0912-v-2353-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-albert-dpo-0912-v-2353-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-albert-dpo-0912-v-2353-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-albert-dpo-0912-v-2353-v3-mkmlizer: ║       /___/                                                         ║
chaiml-albert-dpo-0912-v-2353-v3-mkmlizer: ║                                                                     ║
chaiml-albert-dpo-0912-v-2353-v3-mkmlizer: ║  Version: 0.10.1                                                    ║
chaiml-albert-dpo-0912-v-2353-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-albert-dpo-0912-v-2353-v3-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-albert-dpo-0912-v-2353-v3-mkmlizer: ║                                                                     ║
chaiml-albert-dpo-0912-v-2353-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-albert-dpo-0912-v-2353-v3-mkmlizer: ║  belonging to:                                                      ║
chaiml-albert-dpo-0912-v-2353-v3-mkmlizer: ║                                                                     ║
chaiml-albert-dpo-0912-v-2353-v3-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-albert-dpo-0912-v-2353-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-albert-dpo-0912-v-2353-v3-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-albert-dpo-0912-v-2353-v3-mkmlizer: ║                                                                     ║
chaiml-albert-dpo-0912-v-2353-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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
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', '')
chaiml-albert-dpo-0912-v-2353-v3-mkmlizer: Downloaded to shared memory in 55.242s
chaiml-albert-dpo-0912-v-2353-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpzeffwkxz, device:0
chaiml-albert-dpo-0912-v-2353-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-albert-dpo-0912-v-2353-v3-mkmlizer: quantized model in 40.672s
chaiml-albert-dpo-0912-v-2353-v3-mkmlizer: Processed model ChaiML/albert_dpo_0912_virgo_edit_improved in 95.914s
chaiml-albert-dpo-0912-v-2353-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-albert-dpo-0912-v-2353-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-albert-dpo-0912-v-2353-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-2353-v3
chaiml-albert-dpo-0912-v-2353-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-2353-v3/config.json
chaiml-albert-dpo-0912-v-2353-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-2353-v3/special_tokens_map.json
chaiml-albert-dpo-0912-v-2353-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-2353-v3/tokenizer_config.json
chaiml-albert-dpo-0912-v-2353-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-2353-v3/tokenizer.json
chaiml-albert-dpo-0912-v-2353-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-2353-v3/flywheel_model.0.safetensors
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
chaiml-albert-dpo-0912-v-2353-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 22.87it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 28.17it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:14, 24.63it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:09, 35.89it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:15, 21.21it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:12, 25.81it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:12, 27.01it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:11, 28.63it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:11, 27.53it/s]
Loading 0:  13%|█▎        | 47/363 [00:01<00:10, 30.18it/s]
Loading 0:  14%|█▍        | 51/363 [00:01<00:11, 26.20it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:10, 28.79it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:09, 30.84it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:14, 20.72it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:11, 25.38it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:11, 25.84it/s]
Loading 0:  21%|██        | 77/363 [00:02<00:12, 23.81it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:09, 28.46it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:11, 24.60it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:09, 29.00it/s]
Loading 0:  26%|██▌       | 95/363 [00:03<00:10, 26.07it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:10, 25.16it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:11, 21.99it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:09, 27.01it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:10, 24.89it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:07, 31.51it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 29.81it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 30.93it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 28.84it/s]
Loading 0:  38%|███▊      | 137/363 [00:05<00:07, 29.29it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 25.12it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:09, 23.71it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:09, 22.26it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:07, 28.68it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:07, 27.85it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:07, 28.13it/s]
Loading 0:  46%|████▌     | 167/363 [00:06<00:07, 24.96it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:05, 31.84it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 30.33it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 24.58it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:08, 21.66it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:06, 26.63it/s]
Loading 0:  53%|█████▎    | 194/363 [00:07<00:06, 24.42it/s]
Loading 0:  55%|█████▌    | 201/363 [00:07<00:05, 30.49it/s]
Loading 0:  56%|█████▋    | 205/363 [00:07<00:05, 29.21it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:04, 30.70it/s]
Loading 0:  59%|█████▉    | 214/363 [00:07<00:05, 27.82it/s]
Loading 0:  60%|██████    | 218/363 [00:08<00:05, 28.11it/s]
Loading 0:  61%|██████    | 222/363 [00:08<00:04, 30.23it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:06, 20.89it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:06, 20.93it/s]
Loading 0:  65%|██████▌   | 237/363 [00:08<00:04, 27.79it/s]
Loading 0:  66%|██████▋   | 241/363 [00:09<00:04, 26.64it/s]
Loading 0:  68%|██████▊   | 246/363 [00:09<00:04, 28.82it/s]
Loading 0:  69%|██████▉   | 250/363 [00:09<00:04, 27.68it/s]
Loading 0:  70%|██████▉   | 253/363 [00:09<00:03, 27.96it/s]
Loading 0:  71%|███████   | 257/363 [00:09<00:04, 25.24it/s]
Loading 0:  72%|███████▏  | 263/363 [00:09<00:04, 24.85it/s]
Loading 0:  73%|███████▎  | 266/363 [00:10<00:04, 21.64it/s]
Loading 0:  75%|███████▍  | 272/363 [00:10<00:03, 28.64it/s]
Loading 0:  76%|███████▌  | 276/363 [00:10<00:03, 25.31it/s]
Loading 0:  78%|███████▊  | 282/363 [00:10<00:02, 29.35it/s]
Loading 0:  79%|███████▉  | 286/363 [00:10<00:02, 28.24it/s]
Loading 0:  80%|████████  | 291/363 [00:10<00:02, 30.80it/s]
Loading 0:  81%|████████▏ | 295/363 [00:10<00:02, 29.57it/s]
Loading 0:  82%|████████▏ | 299/363 [00:11<00:02, 29.77it/s]
Loading 0:  83%|████████▎ | 303/363 [00:11<00:01, 31.90it/s]
Loading 0:  85%|████████▍ | 307/363 [00:11<00:02, 21.71it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 21.24it/s]
Loading 0:  88%|████████▊ | 318/363 [00:11<00:01, 27.48it/s]
Loading 0:  89%|████████▊ | 322/363 [00:12<00:01, 26.61it/s]
Loading 0:  90%|█████████ | 327/363 [00:12<00:01, 29.08it/s]
Loading 0:  91%|█████████ | 331/363 [00:12<00:01, 27.95it/s]
Loading 0:  93%|█████████▎| 336/363 [00:12<00:00, 29.80it/s]
Loading 0:  94%|█████████▎| 340/363 [00:12<00:00, 28.28it/s]
Loading 0:  95%|█████████▍| 344/363 [00:19<00:09,  1.98it/s]
Loading 0:  96%|█████████▌| 348/363 [00:19<00:05,  2.67it/s]
Loading 0:  97%|█████████▋| 353/363 [00:19<00:02,  3.86it/s]
Loading 0:  98%|█████████▊| 357/363 [00:20<00:01,  4.99it/s]
                                                            
Job chaiml-albert-dpo-0912-v-2353-v3-mkmlizer completed after 126.75s with status: succeeded
Stopping job with name chaiml-albert-dpo-0912-v-2353-v3-mkmlizer
Pipeline stage MKMLizer completed in 127.49s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-albert-dpo-0912-v-2353-v3
Waiting for inference service chaiml-albert-dpo-0912-v-2353-v3 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', '')
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
Inference service chaiml-albert-dpo-0912-v-2353-v3 ready after 170.61683917045593s
Pipeline stage MKMLDeployer completed in 171.93s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3099896907806396s
Received healthy response to inference request in 1.5224871635437012s
Received healthy response to inference request in 1.233001470565796s
Received healthy response to inference request in 1.3540418148040771s
Received healthy response to inference request in 1.7074291706085205s
5 requests
0 failed requests
5th percentile: 1.2572095394134521
10th percentile: 1.2814176082611084
20th percentile: 1.329833745956421
30th percentile: 1.387730884552002
40th percentile: 1.4551090240478515
50th percentile: 1.5224871635437012
60th percentile: 1.596463966369629
70th percentile: 1.6704407691955565
80th percentile: 1.8279412746429444
90th percentile: 2.068965482711792
95th percentile: 2.1894775867462157
99th percentile: 2.2858872699737547
mean time: 1.625389862060547
Pipeline stage StressChecker completed in 8.79s
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 4.31s
Shutdown handler de-registered
chaiml-albert-dpo-0912-v_2353_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 0.13s
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-v3-profiler
Waiting for inference service chaiml-albert-dpo-0912-v-2353-v3-profiler to be ready
Inference service chaiml-albert-dpo-0912-v-2353-v3-profiler ready after 170.4178433418274s
Pipeline stage MKMLProfilerDeployer completed in 173.27s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-albert-dpo-09dbec6b564e1b62b7ca3b41c51854c296-deplozxckk:/code/chaiverse_profiler_1726378940 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-albert-dpo-09dbec6b564e1b62b7ca3b41c51854c296-deplozxckk --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726378940 && 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_1726378940/summary.json'
kubectl exec -it chaiml-albert-dpo-09dbec6b564e1b62b7ca3b41c51854c296-deplozxckk --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726378940/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1158.19s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-albert-dpo-0912-v-2353-v3-profiler is running
Tearing down inference service chaiml-albert-dpo-0912-v-2353-v3-profiler
Service chaiml-albert-dpo-0912-v-2353-v3-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 6.22s
Shutdown handler de-registered
chaiml-albert-dpo-0912-v_2353_v3 status is now inactive due to auto deactivation removed underperforming models