chaiml-albert-dpo-0912-v_1751

submission_id: chaiml-albert-dpo-0912-v_1751_v4

developer_uid: azuruce

alignment_samples: 10709

alignment_score: 2.3160709889948605

best_of: 8

celo_rating: 1241.43

display_name: edit_original

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_original

latencies: [{'batch_size': 1, 'throughput': 0.6162348511547021, 'latency_mean': 1.6226949834823607, 'latency_p50': 1.6170941591262817, 'latency_p90': 1.7987423658370971}, {'batch_size': 3, 'throughput': 1.0794899376174805, 'latency_mean': 2.7722282552719117, 'latency_p50': 2.7892407178878784, 'latency_p90': 3.0455524921417236}, {'batch_size': 5, 'throughput': 1.230608864639358, 'latency_mean': 4.046758021116257, 'latency_p50': 4.101028919219971, 'latency_p90': 4.50175793170929}, {'batch_size': 6, 'throughput': 1.2496730311381141, 'latency_mean': 4.776713799238205, 'latency_p50': 4.820531010627747, 'latency_p90': 5.3784167766571045}, {'batch_size': 8, 'throughput': 1.232376779841124, 'latency_mean': 6.455991685390472, 'latency_p50': 6.457752585411072, 'latency_p90': 7.226449823379516}, {'batch_size': 10, 'throughput': 1.207845541816638, 'latency_mean': 8.224508279561997, 'latency_p50': 8.25498366355896, 'latency_p90': 9.236169481277466}]

max_input_tokens: 1024

max_output_tokens: 64

model_architecture: MistralForCausalLM

model_group: ChaiML/albert_dpo_0912_v

model_name: edit_original

model_num_parameters: 12772070400.0

model_repo: ChaiML/albert_dpo_0912_virgo_edit_original

model_size: 13B

num_battles: 10706

num_wins: 5267

propriety_score: 0.7301255230125523

propriety_total_count: 956.0

ranking_group: single

status: inactive

submission_type: basic

throughput_3p7s: 1.2

timestamp: 2024-09-15T05:23:05+00:00

us_pacific_date: 2024-09-14

win_ratio: 0.4919671212404259

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-1751-v4-mkmlizer
Waiting for job on chaiml-albert-dpo-0912-v-1751-v4-mkmlizer to finish
chaiml-albert-dpo-0912-v-1751-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-albert-dpo-0912-v-1751-v4-mkmlizer: ║     _____            __           __                                ║
chaiml-albert-dpo-0912-v-1751-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-albert-dpo-0912-v-1751-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-albert-dpo-0912-v-1751-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-albert-dpo-0912-v-1751-v4-mkmlizer: ║       /___/                                                         ║
chaiml-albert-dpo-0912-v-1751-v4-mkmlizer: ║                                                                     ║
chaiml-albert-dpo-0912-v-1751-v4-mkmlizer: ║  Version: 0.10.1                                                    ║
chaiml-albert-dpo-0912-v-1751-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-albert-dpo-0912-v-1751-v4-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-albert-dpo-0912-v-1751-v4-mkmlizer: ║                                                                     ║
chaiml-albert-dpo-0912-v-1751-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-albert-dpo-0912-v-1751-v4-mkmlizer: ║  belonging to:                                                      ║
chaiml-albert-dpo-0912-v-1751-v4-mkmlizer: ║                                                                     ║
chaiml-albert-dpo-0912-v-1751-v4-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-albert-dpo-0912-v-1751-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-albert-dpo-0912-v-1751-v4-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-albert-dpo-0912-v-1751-v4-mkmlizer: ║                                                                     ║
chaiml-albert-dpo-0912-v-1751-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-albert-dpo-0912-v-1751-v4-mkmlizer: Downloaded to shared memory in 81.197s
chaiml-albert-dpo-0912-v-1751-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpp5y2aq3m, device:0
chaiml-albert-dpo-0912-v-1751-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-albert-dpo-0912-v-1751-v4-mkmlizer: quantized model in 40.353s
chaiml-albert-dpo-0912-v-1751-v4-mkmlizer: Processed model ChaiML/albert_dpo_0912_virgo_edit_original in 121.550s
chaiml-albert-dpo-0912-v-1751-v4-mkmlizer: creating bucket guanaco-mkml-models
chaiml-albert-dpo-0912-v-1751-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-albert-dpo-0912-v-1751-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-1751-v4
chaiml-albert-dpo-0912-v-1751-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-1751-v4/config.json
chaiml-albert-dpo-0912-v-1751-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-1751-v4/special_tokens_map.json
chaiml-albert-dpo-0912-v-1751-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-1751-v4/tokenizer_config.json
chaiml-albert-dpo-0912-v-1751-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-1751-v4/tokenizer.json
chaiml-albert-dpo-0912-v-1751-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-1751-v4/flywheel_model.0.safetensors
chaiml-albert-dpo-0912-v-1751-v4-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:14, 24.71it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:11, 30.29it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:13, 26.34it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:09, 37.29it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:15, 21.56it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:13, 24.20it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:11, 28.52it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:12, 25.95it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:10, 30.39it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:11, 27.18it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:09, 31.28it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 26.54it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:11, 25.18it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:09, 29.51it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:09, 28.93it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 28.61it/s]
Loading 0:  23%|██▎       | 84/363 [00:02<00:08, 31.36it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:09, 30.33it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:08, 32.85it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:08, 31.25it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:10, 24.47it/s]
Loading 0:  29%|██▊       | 104/363 [00:03<00:11, 22.31it/s]
Loading 0:  31%|███       | 111/363 [00:03<00:08, 29.63it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:08, 29.18it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:07, 31.99it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:07, 30.89it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 32.80it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 31.33it/s]
Loading 0:  38%|███▊      | 137/363 [00:04<00:07, 31.31it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 26.59it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:08, 24.99it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:09, 23.56it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:06, 30.25it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:06, 29.86it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 32.18it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 30.91it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:05, 33.33it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:05, 31.76it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 25.83it/s]
Loading 0:  51%|█████     | 185/363 [00:06<00:07, 23.05it/s]
Loading 0:  52%|█████▏    | 190/363 [00:06<00:06, 28.36it/s]
Loading 0:  53%|█████▎    | 194/363 [00:06<00:06, 25.82it/s]
Loading 0:  55%|█████▍    | 199/363 [00:06<00:05, 30.74it/s]
Loading 0:  56%|█████▌    | 203/363 [00:07<00:05, 27.40it/s]
Loading 0:  57%|█████▋    | 208/363 [00:07<00:04, 32.19it/s]
Loading 0:  58%|█████▊    | 212/363 [00:07<00:05, 27.70it/s]
Loading 0:  60%|██████    | 218/363 [00:07<00:04, 32.04it/s]
Loading 0:  61%|██████▏   | 223/363 [00:07<00:05, 26.43it/s]
Loading 0:  63%|██████▎   | 227/363 [00:08<00:05, 27.05it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:05, 23.87it/s]
Loading 0:  65%|██████▌   | 237/363 [00:08<00:04, 30.71it/s]
Loading 0:  66%|██████▋   | 241/363 [00:08<00:04, 29.41it/s]
Loading 0:  68%|██████▊   | 246/363 [00:08<00:03, 31.81it/s]
Loading 0:  69%|██████▉   | 250/363 [00:08<00:03, 30.00it/s]
Loading 0:  70%|███████   | 255/363 [00:08<00:03, 31.31it/s]
Loading 0:  71%|███████▏  | 259/363 [00:09<00:03, 30.34it/s]
Loading 0:  72%|███████▏  | 263/363 [00:09<00:04, 23.76it/s]
Loading 0:  73%|███████▎  | 266/363 [00:09<00:04, 21.29it/s]
Loading 0:  75%|███████▌  | 273/363 [00:09<00:03, 28.20it/s]
Loading 0:  76%|███████▋  | 277/363 [00:09<00:03, 27.99it/s]
Loading 0:  78%|███████▊  | 282/363 [00:09<00:02, 30.66it/s]
Loading 0:  79%|███████▉  | 286/363 [00:10<00:02, 29.63it/s]
Loading 0:  80%|████████  | 291/363 [00:10<00:02, 31.83it/s]
Loading 0:  81%|████████▏ | 295/363 [00:10<00:02, 30.79it/s]
Loading 0:  82%|████████▏ | 299/363 [00:10<00:02, 31.05it/s]
Loading 0:  84%|████████▎ | 304/363 [00:10<00:02, 27.08it/s]
Loading 0:  85%|████████▍ | 307/363 [00:10<00:02, 25.37it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 24.08it/s]
Loading 0:  88%|████████▊ | 318/363 [00:11<00:01, 31.09it/s]
Loading 0:  89%|████████▊ | 322/363 [00:11<00:01, 29.34it/s]
Loading 0:  90%|█████████ | 327/363 [00:11<00:01, 31.22it/s]
Loading 0:  91%|█████████ | 331/363 [00:11<00:01, 29.45it/s]
Loading 0:  93%|█████████▎| 336/363 [00:11<00:00, 31.69it/s]
Loading 0:  94%|█████████▎| 340/363 [00:11<00:00, 29.75it/s]
Loading 0:  95%|█████████▍| 344/363 [00:18<00:09,  2.00it/s]
Loading 0:  96%|█████████▌| 348/363 [00:18<00:05,  2.69it/s]
Loading 0:  97%|█████████▋| 353/363 [00:19<00:02,  3.90it/s]
Loading 0:  98%|█████████▊| 357/363 [00:19<00:01,  5.05it/s]
                                                            
Job chaiml-albert-dpo-0912-v-1751-v4-mkmlizer completed after 146.34s with status: succeeded
Stopping job with name chaiml-albert-dpo-0912-v-1751-v4-mkmlizer
Pipeline stage MKMLizer completed in 148.35s
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-1751-v4
Waiting for inference service chaiml-albert-dpo-0912-v-1751-v4 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
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-1751-v4 ready after 170.83950304985046s
Pipeline stage MKMLDeployer completed in 171.19s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.186283588409424s
Received healthy response to inference request in 1.9430196285247803s
Received healthy response to inference request in 1.990450382232666s
Received healthy response to inference request in 1.6469659805297852s
Received healthy response to inference request in 2.113967180252075s
5 requests
0 failed requests
5th percentile: 1.7061767101287841
10th percentile: 1.7653874397277831
20th percentile: 1.8838088989257813
30th percentile: 1.9525057792663574
40th percentile: 1.9714780807495118
50th percentile: 1.990450382232666
60th percentile: 2.03985710144043
70th percentile: 2.0892638206481933
80th percentile: 2.128430461883545
90th percentile: 2.157357025146484
95th percentile: 2.171820306777954
99th percentile: 2.18339093208313
mean time: 1.976137351989746
Pipeline stage StressChecker completed in 11.21s
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 4.21s
Shutdown handler de-registered
chaiml-albert-dpo-0912-v_1751_v4 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 0.15s
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-1751-v4-profiler
Waiting for inference service chaiml-albert-dpo-0912-v-1751-v4-profiler to be ready
Inference service chaiml-albert-dpo-0912-v-1751-v4-profiler ready after 170.38070106506348s
Pipeline stage MKMLProfilerDeployer completed in 170.73s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-albert-dpo-0993c05450d130590d24d798595e20d875-deplostnhp:/code/chaiverse_profiler_1726378337 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-albert-dpo-0993c05450d130590d24d798595e20d875-deplostnhp --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726378337 && 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_1726378337/summary.json'
kubectl exec -it chaiml-albert-dpo-0993c05450d130590d24d798595e20d875-deplostnhp --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726378337/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1167.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-albert-dpo-0912-v-1751-v4-profiler is running
Tearing down inference service chaiml-albert-dpo-0912-v-1751-v4-profiler
Service chaiml-albert-dpo-0912-v-1751-v4-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.78s
Shutdown handler de-registered
chaiml-albert-dpo-0912-v_1751_v4 status is now inactive due to auto deactivation removed underperforming models