submission_id: chaiml-albert-dpo-0912-v_8296_v5
developer_uid: azuruce
alignment_samples: 13020
alignment_score: 0.2811810443283042
best_of: 8
celo_rating: 1246.15
display_name: dpo-ai-selected
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_ai_selected
latencies: [{'batch_size': 1, 'throughput': 0.6183612242671619, 'latency_mean': 1.6171137630939483, 'latency_p50': 1.6158347129821777, 'latency_p90': 1.7825315237045287}, {'batch_size': 3, 'throughput': 1.0772277536937258, 'latency_mean': 2.7717371475696564, 'latency_p50': 2.761368989944458, 'latency_p90': 3.066292238235474}, {'batch_size': 5, 'throughput': 1.2282287632763986, 'latency_mean': 4.04689271569252, 'latency_p50': 4.047646880149841, 'latency_p90': 4.513191604614257}, {'batch_size': 6, 'throughput': 1.2492949750390028, 'latency_mean': 4.777902512550354, 'latency_p50': 4.773119807243347, 'latency_p90': 5.443875670433044}, {'batch_size': 8, 'throughput': 1.2278136537668942, 'latency_mean': 6.474300911426544, 'latency_p50': 6.505697846412659, 'latency_p90': 7.366948413848877}, {'batch_size': 10, 'throughput': 1.1995865324350552, 'latency_mean': 8.274209036827088, 'latency_p50': 8.323027729988098, 'latency_p90': 9.316802883148194}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: ChaiML/albert_dpo_0912_v
model_name: dpo-ai-selected
model_num_parameters: 12772070400.0
model_repo: ChaiML/albert_dpo_0912_virgo_edit_ai_selected
model_size: 13B
num_battles: 13019
num_wins: 6498
propriety_score: 0.7323704333050127
propriety_total_count: 1177.0
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 1.2
timestamp: 2024-09-15T05:22:23+00:00
us_pacific_date: 2024-09-14
win_ratio: 0.4991166756279284
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-v5-mkmlizer
Waiting for job on chaiml-albert-dpo-0912-v-8296-v5-mkmlizer to finish
chaiml-albert-dpo-0912-v-8296-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-albert-dpo-0912-v-8296-v5-mkmlizer: ║ _____ __ __ ║
chaiml-albert-dpo-0912-v-8296-v5-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-albert-dpo-0912-v-8296-v5-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-albert-dpo-0912-v-8296-v5-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-albert-dpo-0912-v-8296-v5-mkmlizer: ║ /___/ ║
chaiml-albert-dpo-0912-v-8296-v5-mkmlizer: ║ ║
chaiml-albert-dpo-0912-v-8296-v5-mkmlizer: ║ Version: 0.10.1 ║
chaiml-albert-dpo-0912-v-8296-v5-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-albert-dpo-0912-v-8296-v5-mkmlizer: ║ https://mk1.ai ║
chaiml-albert-dpo-0912-v-8296-v5-mkmlizer: ║ ║
chaiml-albert-dpo-0912-v-8296-v5-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-albert-dpo-0912-v-8296-v5-mkmlizer: ║ belonging to: ║
chaiml-albert-dpo-0912-v-8296-v5-mkmlizer: ║ ║
chaiml-albert-dpo-0912-v-8296-v5-mkmlizer: ║ Chai Research Corp. ║
chaiml-albert-dpo-0912-v-8296-v5-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-albert-dpo-0912-v-8296-v5-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-albert-dpo-0912-v-8296-v5-mkmlizer: ║ ║
chaiml-albert-dpo-0912-v-8296-v5-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
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-8296-v5-mkmlizer: Downloaded to shared memory in 75.239s
chaiml-albert-dpo-0912-v-8296-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpzdfcmy5n, device:0
chaiml-albert-dpo-0912-v-8296-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
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-8296-v5-mkmlizer: quantized model in 41.397s
chaiml-albert-dpo-0912-v-8296-v5-mkmlizer: Processed model ChaiML/albert_dpo_0912_virgo_edit_ai_selected in 116.636s
chaiml-albert-dpo-0912-v-8296-v5-mkmlizer: creating bucket guanaco-mkml-models
chaiml-albert-dpo-0912-v-8296-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-albert-dpo-0912-v-8296-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-8296-v5
chaiml-albert-dpo-0912-v-8296-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-8296-v5/config.json
chaiml-albert-dpo-0912-v-8296-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-8296-v5/special_tokens_map.json
chaiml-albert-dpo-0912-v-8296-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-8296-v5/tokenizer_config.json
chaiml-albert-dpo-0912-v-8296-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-8296-v5/tokenizer.json
chaiml-albert-dpo-0912-v-8296-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-8296-v5/flywheel_model.0.safetensors
chaiml-albert-dpo-0912-v-8296-v5-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:16, 21.56it/s] Loading 0: 3%|▎ | 10/363 [00:00<00:13, 26.87it/s] Loading 0: 4%|▍ | 14/363 [00:00<00:15, 23.25it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:11, 29.28it/s] Loading 0: 6%|▋ | 23/363 [00:00<00:15, 22.18it/s] Loading 0: 7%|▋ | 26/363 [00:01<00:16, 20.14it/s] Loading 0: 9%|▊ | 31/363 [00:01<00:12, 25.86it/s] Loading 0: 10%|▉ | 35/363 [00:01<00:11, 28.10it/s] Loading 0: 11%|█ | 39/363 [00:01<00:10, 30.33it/s] Loading 0: 12%|█▏ | 43/363 [00:01<00:10, 29.22it/s] Loading 0: 13%|█▎ | 48/363 [00:01<00:09, 32.04it/s] Loading 0: 14%|█▍ | 52/363 [00:01<00:10, 30.26it/s] Loading 0: 15%|█▌ | 56/363 [00:02<00:09, 31.12it/s] Loading 0: 17%|█▋ | 61/363 [00:02<00:10, 28.22it/s] Loading 0: 18%|█▊ | 64/363 [00:02<00:12, 23.54it/s] Loading 0: 20%|█▉ | 71/363 [00:02<00:09, 30.94it/s] Loading 0: 21%|██ | 75/363 [00:02<00:09, 30.62it/s] Loading 0: 22%|██▏ | 79/363 [00:02<00:09, 29.75it/s] Loading 0: 23%|██▎ | 84/363 [00:02<00:08, 32.57it/s] Loading 0: 24%|██▍ | 88/363 [00:03<00:08, 31.27it/s] Loading 0: 26%|██▌ | 93/363 [00:03<00:08, 33.23it/s] Loading 0: 27%|██▋ | 97/363 [00:03<00:08, 31.01it/s] Loading 0: 28%|██▊ | 101/363 [00:03<00:10, 25.91it/s] Loading 0: 29%|██▊ | 104/363 [00:03<00:11, 22.37it/s] Loading 0: 31%|███ | 111/363 [00:03<00:08, 29.12it/s] Loading 0: 32%|███▏ | 115/363 [00:04<00:09, 27.00it/s] Loading 0: 33%|███▎ | 120/363 [00:04<00:08, 28.68it/s] Loading 0: 34%|███▍ | 123/363 [00:04<00:09, 25.68it/s] Loading 0: 35%|███▍ | 127/363 [00:04<00:08, 28.19it/s] Loading 0: 36%|███▌ | 131/363 [00:04<00:09, 24.77it/s] Loading 0: 38%|███▊ | 137/363 [00:04<00:07, 29.14it/s] Loading 0: 39%|███▉ | 141/363 [00:05<00:07, 31.36it/s] Loading 0: 40%|███▉ | 145/363 [00:05<00:10, 21.17it/s] Loading 0: 41%|████ | 148/363 [00:05<00:09, 22.70it/s] Loading 0: 42%|████▏ | 151/363 [00:05<00:09, 22.89it/s] Loading 0: 42%|████▏ | 154/363 [00:05<00:08, 24.24it/s] Loading 0: 43%|████▎ | 157/363 [00:05<00:08, 25.51it/s] Loading 0: 44%|████▍ | 160/363 [00:05<00:08, 25.27it/s] Loading 0: 45%|████▍ | 163/363 [00:06<00:07, 26.12it/s] Loading 0: 46%|████▌ | 167/363 [00:06<00:08, 22.71it/s] Loading 0: 47%|████▋ | 172/363 [00:06<00:06, 28.20it/s] Loading 0: 48%|████▊ | 176/363 [00:06<00:07, 24.43it/s] Loading 0: 50%|████▉ | 181/363 [00:06<00:06, 29.10it/s] Loading 0: 51%|█████ | 185/363 [00:07<00:09, 18.84it/s] Loading 0: 52%|█████▏ | 190/363 [00:07<00:07, 23.55it/s] Loading 0: 53%|█████▎ | 194/363 [00:07<00:07, 21.98it/s] Loading 0: 55%|█████▍ | 199/363 [00:07<00:06, 26.87it/s] Loading 0: 56%|█████▌ | 203/363 [00:07<00:06, 24.50it/s] Loading 0: 58%|█████▊ | 210/363 [00:07<00:04, 31.33it/s] Loading 0: 59%|█████▉ | 214/363 [00:07<00:04, 30.32it/s] Loading 0: 60%|██████ | 218/363 [00:08<00:04, 30.58it/s] Loading 0: 61%|██████▏ | 223/363 [00:08<00:05, 26.76it/s] Loading 0: 62%|██████▏ | 226/363 [00:08<00:05, 25.06it/s] Loading 0: 63%|██████▎ | 230/363 [00:08<00:05, 23.68it/s] Loading 0: 65%|██████▌ | 237/363 [00:08<00:04, 30.59it/s] Loading 0: 66%|██████▋ | 241/363 [00:08<00:04, 29.13it/s] Loading 0: 68%|██████▊ | 246/363 [00:09<00:03, 31.67it/s] Loading 0: 69%|██████▉ | 250/363 [00:09<00:03, 30.01it/s] Loading 0: 70%|███████ | 255/363 [00:09<00:03, 32.43it/s] Loading 0: 71%|███████▏ | 259/363 [00:09<00:03, 30.90it/s] Loading 0: 72%|███████▏ | 263/363 [00:09<00:03, 25.19it/s] Loading 0: 73%|███████▎ | 266/363 [00:09<00:04, 22.10it/s] Loading 0: 75%|███████▌ | 273/363 [00:10<00:03, 29.17it/s] Loading 0: 76%|███████▋ | 277/363 [00:10<00:03, 28.30it/s] Loading 0: 78%|███████▊ | 282/363 [00:10<00:02, 29.51it/s] Loading 0: 79%|███████▉ | 286/363 [00:10<00:02, 27.96it/s] Loading 0: 80%|████████ | 291/363 [00:10<00:02, 30.11it/s] Loading 0: 81%|████████▏ | 295/363 [00:10<00:02, 28.77it/s] Loading 0: 82%|████████▏ | 299/363 [00:10<00:02, 29.48it/s] Loading 0: 84%|████████▎ | 304/363 [00:11<00:02, 25.89it/s] Loading 0: 85%|████████▍ | 307/363 [00:11<00:02, 24.55it/s] Loading 0: 86%|████████▌ | 311/363 [00:11<00:02, 22.82it/s] Loading 0: 87%|████████▋ | 316/363 [00:11<00:01, 27.06it/s] Loading 0: 88%|████████▊ | 320/363 [00:11<00:01, 24.54it/s] Loading 0: 90%|████████▉ | 326/363 [00:12<00:01, 31.58it/s] Loading 0: 91%|█████████ | 330/363 [00:12<00:01, 27.49it/s] Loading 0: 93%|█████████▎| 336/363 [00:12<00:00, 31.95it/s] Loading 0: 94%|█████████▎| 340/363 [00:12<00:00, 30.93it/s] Loading 0: 95%|█████████▍| 344/363 [00:19<00:09, 2.04it/s] Loading 0: 96%|█████████▌| 348/363 [00:19<00:05, 2.72it/s] Loading 0: 97%|█████████▋| 353/363 [00:19<00:02, 3.92it/s] Loading 0: 98%|█████████▊| 357/363 [00:19<00:01, 5.03it/s]
Job chaiml-albert-dpo-0912-v-8296-v5-mkmlizer completed after 146.0s with status: succeeded
Stopping job with name chaiml-albert-dpo-0912-v-8296-v5-mkmlizer
Pipeline stage MKMLizer completed in 146.87s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.58s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-albert-dpo-0912-v-8296-v5
Waiting for inference service chaiml-albert-dpo-0912-v-8296-v5 to be ready
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-8296-v5 ready after 171.64467406272888s
Pipeline stage MKMLDeployer completed in 172.02s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.731696367263794s
Received healthy response to inference request in 1.742537021636963s
Received healthy response to inference request in 2.182811975479126s
Received healthy response to inference request in 2.1854827404022217s
Received healthy response to inference request in 1.714313268661499s
5 requests
0 failed requests
5th percentile: 1.7199580192565918
10th percentile: 1.7256027698516845
20th percentile: 1.7368922710418702
30th percentile: 1.8305920124053956
40th percentile: 2.0067019939422606
50th percentile: 2.182811975479126
60th percentile: 2.1838802814483644
70th percentile: 2.1849485874176025
80th percentile: 2.2947254657745364
90th percentile: 2.513210916519165
95th percentile: 2.6224536418914792
99th percentile: 2.709847822189331
mean time: 2.111368274688721
Pipeline stage StressChecker completed in 11.48s
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 7.97s
Shutdown handler de-registered
chaiml-albert-dpo-0912-v_8296_v5 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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-albert-dpo-0912-v-8296-v5-profiler
Waiting for inference service chaiml-albert-dpo-0912-v-8296-v5-profiler to be ready
Inference service chaiml-albert-dpo-0912-v-8296-v5-profiler ready after 170.40459990501404s
Pipeline stage MKMLProfilerDeployer completed in 175.02s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-albert-dpo-09ad5d3153068730bd19abc57b27f470bd-deploql8rl:/code/chaiverse_profiler_1726378297 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-albert-dpo-09ad5d3153068730bd19abc57b27f470bd-deploql8rl --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-09ad5d3153068730bd19abc57b27f470bd-deploql8rl --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726378297/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1169.25s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-albert-dpo-0912-v-8296-v5-profiler is running
Tearing down inference service chaiml-albert-dpo-0912-v-8296-v5-profiler
Service chaiml-albert-dpo-0912-v-8296-v5-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.05s
Shutdown handler de-registered
chaiml-albert-dpo-0912-v_8296_v5 status is now inactive due to auto deactivation removed underperforming models