chaiml-albert-dpo-0912-v_2291

submission_id: chaiml-albert-dpo-0912-v_2291_v1

developer_uid: chai_backend_admin

alignment_samples: 13329

alignment_score: 0.8731855970344173

best_of: 8

celo_rating: 1244.1

display_name: virgo-edit-romance

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_variety_romance

latencies: [{'batch_size': 1, 'throughput': 0.6121673579425043, 'latency_mean': 1.6334611797332763, 'latency_p50': 1.6330941915512085, 'latency_p90': 1.8159351110458375}, {'batch_size': 3, 'throughput': 1.0639194999241695, 'latency_mean': 2.8079142498970033, 'latency_p50': 2.82416832447052, 'latency_p90': 3.089168095588684}, {'batch_size': 5, 'throughput': 1.210070181580172, 'latency_mean': 4.11413432598114, 'latency_p50': 4.119624018669128, 'latency_p90': 4.6100159883499146}, {'batch_size': 6, 'throughput': 1.2355513366561648, 'latency_mean': 4.833591116666794, 'latency_p50': 4.885304093360901, 'latency_p90': 5.385783243179321}, {'batch_size': 8, 'throughput': 1.2125784704051699, 'latency_mean': 6.574465918540954, 'latency_p50': 6.637212634086609, 'latency_p90': 7.396404075622558}, {'batch_size': 10, 'throughput': 1.1940325530774691, 'latency_mean': 8.31973788022995, 'latency_p50': 8.352401971817017, 'latency_p90': 9.502055239677428}]

max_input_tokens: 1024

max_output_tokens: 64

model_architecture: MistralForCausalLM

model_group: ChaiML/albert_dpo_0912_v

model_name: virgo-edit-romance

model_num_parameters: 12772070400.0

model_repo: ChaiML/albert_dpo_0912_virgo_edit_variety_romance

model_size: 13B

num_battles: 13328

num_wins: 6626

propriety_score: 0.7626527050610821

propriety_total_count: 1146.0

ranking_group: single

status: inactive

submission_type: basic

throughput_3p7s: 1.18

timestamp: 2024-09-13T20:22:26+00:00

us_pacific_date: 2024-09-13

win_ratio: 0.49714885954381755

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-2291-v1-mkmlizer
Waiting for job on chaiml-albert-dpo-0912-v-2291-v1-mkmlizer to finish
chaiml-albert-dpo-0912-v-2291-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-albert-dpo-0912-v-2291-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-albert-dpo-0912-v-2291-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-albert-dpo-0912-v-2291-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-albert-dpo-0912-v-2291-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-albert-dpo-0912-v-2291-v1-mkmlizer: ║       /___/                                                         ║
chaiml-albert-dpo-0912-v-2291-v1-mkmlizer: ║                                                                     ║
chaiml-albert-dpo-0912-v-2291-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
chaiml-albert-dpo-0912-v-2291-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-albert-dpo-0912-v-2291-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-albert-dpo-0912-v-2291-v1-mkmlizer: ║                                                                     ║
chaiml-albert-dpo-0912-v-2291-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-albert-dpo-0912-v-2291-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-albert-dpo-0912-v-2291-v1-mkmlizer: ║                                                                     ║
chaiml-albert-dpo-0912-v-2291-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-albert-dpo-0912-v-2291-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-albert-dpo-0912-v-2291-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-albert-dpo-0912-v-2291-v1-mkmlizer: ║                                                                     ║
chaiml-albert-dpo-0912-v-2291-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-albert-dpo-0912-v-2291-v1-mkmlizer: Downloaded to shared memory in 94.283s
chaiml-albert-dpo-0912-v-2291-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpfss_tlma, device:0
chaiml-albert-dpo-0912-v-2291-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-albert-dpo-0912-v-2291-v1-mkmlizer: quantized model in 40.202s
chaiml-albert-dpo-0912-v-2291-v1-mkmlizer: Processed model ChaiML/albert_dpo_0912_virgo_edit_variety_romance in 134.486s
chaiml-albert-dpo-0912-v-2291-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-albert-dpo-0912-v-2291-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-albert-dpo-0912-v-2291-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-2291-v1
chaiml-albert-dpo-0912-v-2291-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-2291-v1/config.json
chaiml-albert-dpo-0912-v-2291-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-2291-v1/special_tokens_map.json
chaiml-albert-dpo-0912-v-2291-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-2291-v1/tokenizer_config.json
chaiml-albert-dpo-0912-v-2291-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-2291-v1/tokenizer.json
chaiml-albert-dpo-0912-v-2291-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-2291-v1/flywheel_model.0.safetensors
chaiml-albert-dpo-0912-v-2291-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 23.08it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 29.07it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:13, 26.00it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:09, 36.79it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:16, 20.63it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:14, 23.56it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:10, 29.70it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:10, 29.36it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 31.50it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 30.28it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:10, 29.82it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 26.13it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:13, 22.79it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:09, 29.80it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:09, 29.56it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 28.55it/s]
Loading 0:  23%|██▎       | 84/363 [00:02<00:09, 30.68it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:09, 29.99it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:08, 32.34it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:08, 31.09it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:10, 25.00it/s]
Loading 0:  29%|██▊       | 104/363 [00:03<00:11, 22.04it/s]
Loading 0:  31%|███       | 111/363 [00:03<00:08, 29.15it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:08, 28.50it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:07, 30.41it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 29.65it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 31.93it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 30.87it/s]
Loading 0:  38%|███▊      | 137/363 [00:04<00:07, 31.03it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 27.00it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:08, 25.25it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:08, 24.37it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:06, 31.38it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:06, 30.36it/s]
Loading 0:  45%|████▌     | 164/363 [00:05<00:06, 30.87it/s]
Loading 0:  46%|████▋     | 168/363 [00:05<00:07, 27.54it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:05, 31.82it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 30.66it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 25.32it/s]
Loading 0:  51%|█████     | 185/363 [00:06<00:07, 22.81it/s]
Loading 0:  53%|█████▎    | 192/363 [00:06<00:05, 30.01it/s]
Loading 0:  54%|█████▍    | 196/363 [00:06<00:05, 28.97it/s]
Loading 0:  55%|█████▌    | 201/363 [00:07<00:05, 31.53it/s]
Loading 0:  56%|█████▋    | 205/363 [00:07<00:05, 30.50it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:04, 32.96it/s]
Loading 0:  59%|█████▉    | 214/363 [00:07<00:04, 30.95it/s]
Loading 0:  60%|██████    | 218/363 [00:07<00:04, 30.28it/s]
Loading 0:  61%|██████▏   | 223/363 [00:07<00:05, 26.80it/s]
Loading 0:  62%|██████▏   | 226/363 [00:07<00:05, 25.47it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:05, 24.23it/s]
Loading 0:  65%|██████▌   | 237/363 [00:08<00:04, 31.29it/s]
Loading 0:  66%|██████▋   | 241/363 [00:08<00:04, 30.04it/s]
Loading 0:  68%|██████▊   | 246/363 [00:08<00:03, 31.47it/s]
Loading 0:  69%|██████▉   | 250/363 [00:08<00:03, 30.53it/s]
Loading 0:  70%|███████   | 255/363 [00:08<00:03, 32.72it/s]
Loading 0:  71%|███████▏  | 259/363 [00:09<00:03, 30.91it/s]
Loading 0:  72%|███████▏  | 263/363 [00:09<00:03, 25.35it/s]
Loading 0:  73%|███████▎  | 266/363 [00:09<00:04, 22.50it/s]
Loading 0:  75%|███████▌  | 273/363 [00:09<00:03, 29.58it/s]
Loading 0:  76%|███████▋  | 277/363 [00:09<00:02, 29.15it/s]
Loading 0:  78%|███████▊  | 282/363 [00:09<00:02, 31.60it/s]
Loading 0:  79%|███████▉  | 286/363 [00:09<00:02, 30.52it/s]
Loading 0:  80%|████████  | 291/363 [00:10<00:02, 32.74it/s]
Loading 0:  81%|████████▏ | 295/363 [00:10<00:02, 31.38it/s]
Loading 0:  82%|████████▏ | 299/363 [00:10<00:02, 31.36it/s]
Loading 0:  84%|████████▎ | 304/363 [00:10<00:02, 26.74it/s]
Loading 0:  85%|████████▍ | 307/363 [00:10<00:02, 24.94it/s]
Loading 0:  86%|████████▌ | 311/363 [00:10<00:02, 24.06it/s]
Loading 0:  88%|████████▊ | 318/363 [00:11<00:01, 31.14it/s]
Loading 0:  89%|████████▊ | 322/363 [00:11<00:01, 29.89it/s]
Loading 0:  90%|█████████ | 327/363 [00:11<00:01, 31.82it/s]
Loading 0:  91%|█████████ | 331/363 [00:11<00:01, 30.37it/s]
Loading 0:  93%|█████████▎| 336/363 [00:11<00:00, 32.02it/s]
Loading 0:  94%|█████████▎| 340/363 [00:11<00:00, 30.79it/s]
Loading 0:  95%|█████████▍| 344/363 [00:18<00:09,  2.01it/s]
Loading 0:  96%|█████████▌| 348/363 [00:18<00:05,  2.71it/s]
Loading 0:  97%|█████████▋| 353/363 [00:18<00:02,  3.93it/s]
Loading 0:  98%|█████████▊| 357/363 [00:19<00:01,  5.10it/s]
                                                            
Job chaiml-albert-dpo-0912-v-2291-v1-mkmlizer completed after 157.88s with status: succeeded
Stopping job with name chaiml-albert-dpo-0912-v-2291-v1-mkmlizer
Pipeline stage MKMLizer completed in 160.20s
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-2291-v1
Waiting for inference service chaiml-albert-dpo-0912-v-2291-v1 to be ready
Inference service chaiml-albert-dpo-0912-v-2291-v1 ready after 180.7187032699585s
Pipeline stage MKMLDeployer completed in 181.11s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.009669542312622s
Received healthy response to inference request in 2.11519718170166s
Received healthy response to inference request in 1.8228254318237305s
Received healthy response to inference request in 1.799231767654419s
Received healthy response to inference request in 1.3266990184783936s
5 requests
0 failed requests
5th percentile: 1.4212055683135987
10th percentile: 1.5157121181488038
20th percentile: 1.7047252178192138
30th percentile: 1.8039505004882812
40th percentile: 1.813387966156006
50th percentile: 1.8228254318237305
60th percentile: 1.8975630760192872
70th percentile: 1.9723007202148437
80th percentile: 2.0307750701904297
90th percentile: 2.072986125946045
95th percentile: 2.0940916538238525
99th percentile: 2.1109760761260987
mean time: 1.814724588394165
Pipeline stage StressChecker completed in 10.02s
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 7.84s
Shutdown handler de-registered
chaiml-albert-dpo-0912-v_2291_v1 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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-albert-dpo-0912-v-2291-v1-profiler
Waiting for inference service chaiml-albert-dpo-0912-v-2291-v1-profiler to be ready
Inference service chaiml-albert-dpo-0912-v-2291-v1-profiler ready after 180.431987285614s
Pipeline stage MKMLProfilerDeployer completed in 180.84s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-albert-dpo-094380521ed2e72fbe07f61ca3e3913556-deplogbw8m:/code/chaiverse_profiler_1726259525 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-albert-dpo-094380521ed2e72fbe07f61ca3e3913556-deplogbw8m --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726259525 && 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_1726259525/summary.json'
kubectl exec -it chaiml-albert-dpo-094380521ed2e72fbe07f61ca3e3913556-deplogbw8m --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726259525/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1180.52s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-albert-dpo-0912-v-2291-v1-profiler is running
Tearing down inference service chaiml-albert-dpo-0912-v-2291-v1-profiler
Service chaiml-albert-dpo-0912-v-2291-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.90s
Shutdown handler de-registered
chaiml-albert-dpo-0912-v_2291_v1 status is now inactive due to auto deactivation removed underperforming models