jic062-dpo-v1-4-c500

submission_id: jic062-dpo-v1-4-c500_v2

developer_uid: chace9580

alignment_samples: 14411

alignment_score: 0.60353021845158

best_of: 16

celo_rating: 1249.37

display_name: jic062-dpo-v1-4-c500_v1

formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '|eot_id|', '|end_header_id|'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}

gpu_counts: {'NVIDIA RTX A5000': 1}

is_internal_developer: False

language_model: jic062/dpo-v1.4-c500

latencies: [{'batch_size': 1, 'throughput': 0.8983404917071192, 'latency_mean': 1.1131040024757386, 'latency_p50': 1.1094671487808228, 'latency_p90': 1.2346838474273683}, {'batch_size': 3, 'throughput': 1.5782686933491783, 'latency_mean': 1.8963203847408294, 'latency_p50': 1.8965474367141724, 'latency_p90': 2.1292937994003296}, {'batch_size': 5, 'throughput': 1.7227629938416447, 'latency_mean': 2.8900255227088927, 'latency_p50': 2.853773832321167, 'latency_p90': 3.231691098213196}, {'batch_size': 6, 'throughput': 1.7452550504864048, 'latency_mean': 3.421988126039505, 'latency_p50': 3.4452861547470093, 'latency_p90': 3.851968455314636}, {'batch_size': 8, 'throughput': 1.7450483649784458, 'latency_mean': 4.5585196387767795, 'latency_p50': 4.562340259552002, 'latency_p90': 5.115764331817627}, {'batch_size': 10, 'throughput': 1.73646202259271, 'latency_mean': 5.701856801509857, 'latency_p50': 5.729152798652649, 'latency_p90': 6.595565271377564}]

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_group: jic062/dpo-v1.4-c500

model_name: jic062-dpo-v1-4-c500_v1

model_num_parameters: 8030261248.0

model_repo: jic062/dpo-v1.4-c500

model_size: 8B

num_battles: 14408

num_wins: 7371

propriety_score: 0.7514033680834001

propriety_total_count: 1247.0

ranking_group: single

status: inactive

submission_type: basic

throughput_3p7s: 1.75

timestamp: 2024-09-08T19:19:41+00:00

us_pacific_date: 2024-09-08

win_ratio: 0.5115907828983898

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 jic062-dpo-v1-4-c500-v2-mkmlizer
Waiting for job on jic062-dpo-v1-4-c500-v2-mkmlizer to finish
jic062-dpo-v1-4-c500-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jic062-dpo-v1-4-c500-v2-mkmlizer: ║     _____            __           __                                ║
jic062-dpo-v1-4-c500-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
jic062-dpo-v1-4-c500-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
jic062-dpo-v1-4-c500-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
jic062-dpo-v1-4-c500-v2-mkmlizer: ║       /___/                                                         ║
jic062-dpo-v1-4-c500-v2-mkmlizer: ║                                                                     ║
jic062-dpo-v1-4-c500-v2-mkmlizer: ║  Version: 0.10.1                                                    ║
jic062-dpo-v1-4-c500-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
jic062-dpo-v1-4-c500-v2-mkmlizer: ║  https://mk1.ai                                                     ║
jic062-dpo-v1-4-c500-v2-mkmlizer: ║                                                                     ║
jic062-dpo-v1-4-c500-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
jic062-dpo-v1-4-c500-v2-mkmlizer: ║  belonging to:                                                      ║
jic062-dpo-v1-4-c500-v2-mkmlizer: ║                                                                     ║
jic062-dpo-v1-4-c500-v2-mkmlizer: ║  Chai Research Corp.                                                ║
jic062-dpo-v1-4-c500-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
jic062-dpo-v1-4-c500-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
jic062-dpo-v1-4-c500-v2-mkmlizer: ║                                                                     ║
jic062-dpo-v1-4-c500-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jic062-dpo-v1-4-c500-v2-mkmlizer: Downloaded to shared memory in 21.278s
jic062-dpo-v1-4-c500-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpxfmicgb9, device:0
jic062-dpo-v1-4-c500-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jic062-dpo-v1-4-c500-v2-mkmlizer: quantized model in 25.747s
jic062-dpo-v1-4-c500-v2-mkmlizer: Processed model jic062/dpo-v1.4-c500 in 47.026s
jic062-dpo-v1-4-c500-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jic062-dpo-v1-4-c500-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jic062-dpo-v1-4-c500-v2
jic062-dpo-v1-4-c500-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jic062-dpo-v1-4-c500-v2/config.json
jic062-dpo-v1-4-c500-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jic062-dpo-v1-4-c500-v2/special_tokens_map.json
jic062-dpo-v1-4-c500-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jic062-dpo-v1-4-c500-v2/tokenizer_config.json
jic062-dpo-v1-4-c500-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jic062-dpo-v1-4-c500-v2/tokenizer.json
jic062-dpo-v1-4-c500-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jic062-dpo-v1-4-c500-v2/flywheel_model.0.safetensors
jic062-dpo-v1-4-c500-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:08, 35.65it/s]
Loading 0:   5%|▍         | 14/291 [00:00<00:05, 49.00it/s]
Loading 0:   8%|▊         | 23/291 [00:00<00:05, 53.46it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:04, 58.34it/s]
Loading 0:  13%|█▎        | 37/291 [00:00<00:04, 52.99it/s]
Loading 0:  15%|█▌        | 44/291 [00:00<00:04, 56.87it/s]
Loading 0:  17%|█▋        | 50/291 [00:00<00:04, 50.80it/s]
Loading 0:  20%|██        | 59/291 [00:01<00:04, 52.76it/s]
Loading 0:  23%|██▎       | 68/291 [00:01<00:04, 53.85it/s]
Loading 0:  26%|██▌       | 76/291 [00:01<00:03, 59.34it/s]
Loading 0:  29%|██▊       | 83/291 [00:01<00:05, 41.14it/s]
Loading 0:  30%|███       | 88/291 [00:01<00:04, 41.38it/s]
Loading 0:  33%|███▎      | 95/291 [00:01<00:04, 41.84it/s]
Loading 0:  36%|███▌      | 104/291 [00:02<00:04, 45.77it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:03, 52.50it/s]
Loading 0:  41%|████      | 118/291 [00:02<00:03, 50.03it/s]
Loading 0:  43%|████▎     | 124/291 [00:02<00:03, 51.61it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:03, 53.59it/s]
Loading 0:  47%|████▋     | 136/291 [00:02<00:03, 51.02it/s]
Loading 0:  49%|████▉     | 142/291 [00:02<00:02, 51.76it/s]
Loading 0:  51%|█████     | 149/291 [00:02<00:02, 47.70it/s]
Loading 0:  54%|█████▎    | 156/291 [00:03<00:02, 52.46it/s]
Loading 0:  56%|█████▌    | 162/291 [00:03<00:02, 53.71it/s]
Loading 0:  58%|█████▊    | 168/291 [00:03<00:02, 48.33it/s]
Loading 0:  60%|██████    | 176/291 [00:03<00:02, 55.59it/s]
Loading 0:  63%|██████▎   | 182/291 [00:03<00:02, 49.04it/s]
Loading 0:  65%|██████▍   | 188/291 [00:03<00:02, 38.29it/s]
Loading 0:  66%|██████▋   | 193/291 [00:03<00:02, 39.43it/s]
Loading 0:  68%|██████▊   | 199/291 [00:04<00:02, 40.99it/s]
Loading 0:  70%|███████   | 204/291 [00:04<00:02, 41.58it/s]
Loading 0:  73%|███████▎  | 211/291 [00:04<00:01, 47.18it/s]
Loading 0:  75%|███████▍  | 217/291 [00:04<00:01, 45.87it/s]
Loading 0:  76%|███████▋  | 222/291 [00:04<00:01, 46.29it/s]
Loading 0:  79%|███████▊  | 229/291 [00:04<00:01, 52.23it/s]
Loading 0:  81%|████████  | 235/291 [00:04<00:01, 50.18it/s]
Loading 0:  83%|████████▎ | 241/291 [00:04<00:00, 52.00it/s]
Loading 0:  85%|████████▍ | 247/291 [00:05<00:00, 54.02it/s]
Loading 0:  87%|████████▋ | 253/291 [00:05<00:00, 49.09it/s]
Loading 0:  89%|████████▉ | 259/291 [00:05<00:00, 49.78it/s]
Loading 0:  91%|█████████ | 265/291 [00:05<00:00, 50.19it/s]
Loading 0:  93%|█████████▎| 271/291 [00:05<00:00, 45.37it/s]
Loading 0:  95%|█████████▍| 276/291 [00:05<00:00, 44.80it/s]
Loading 0:  97%|█████████▋| 282/291 [00:05<00:00, 42.61it/s]
Loading 0:  99%|█████████▊| 287/291 [00:11<00:01,  3.24it/s]
                                                            
Job jic062-dpo-v1-4-c500-v2-mkmlizer completed after 64.53s with status: succeeded
Stopping job with name jic062-dpo-v1-4-c500-v2-mkmlizer
Pipeline stage MKMLizer completed in 66.18s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.28s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service jic062-dpo-v1-4-c500-v2
Waiting for inference service jic062-dpo-v1-4-c500-v2 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
Inference service jic062-dpo-v1-4-c500-v2 ready after 150.68559861183167s
Pipeline stage MKMLDeployer completed in 151.20s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.395526885986328s
Received healthy response to inference request in 2.0574541091918945s
Received healthy response to inference request in 1.7869131565093994s
Received healthy response to inference request in 1.5922601222991943s
Received healthy response to inference request in 2.184478282928467s
5 requests
0 failed requests
5th percentile: 1.6311907291412353
10th percentile: 1.6701213359832763
20th percentile: 1.7479825496673584
30th percentile: 1.8410213470458985
40th percentile: 1.9492377281188964
50th percentile: 2.0574541091918945
60th percentile: 2.1082637786865233
70th percentile: 2.1590734481811524
80th percentile: 2.226688003540039
90th percentile: 2.3111074447631834
95th percentile: 2.3533171653747558
99th percentile: 2.3870849418640137
mean time: 2.0033265113830567
Pipeline stage StressChecker completed in 10.90s
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 5.02s
Shutdown handler de-registered
jic062-dpo-v1-4-c500_v2 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 0.12s
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 jic062-dpo-v1-4-c500-v2-profiler
Waiting for inference service jic062-dpo-v1-4-c500-v2-profiler to be ready
Inference service jic062-dpo-v1-4-c500-v2-profiler ready after 150.35463690757751s
Pipeline stage MKMLProfilerDeployer completed in 150.73s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/jic062-dpo-v1-4-c500-v2-profiler-predictor-00001-deploymenxlx94:/code/chaiverse_profiler_1725823609 --namespace tenant-chaiml-guanaco
kubectl exec -it jic062-dpo-v1-4-c500-v2-profiler-predictor-00001-deploymenxlx94 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725823609 && python profiles.py profile --best_of_n 16 --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 512 --output_tokens 64 --summary /code/chaiverse_profiler_1725823609/summary.json'
kubectl exec -it jic062-dpo-v1-4-c500-v2-profiler-predictor-00001-deploymenxlx94 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725823609/summary.json'
Pipeline stage MKMLProfilerRunner completed in 815.84s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service jic062-dpo-v1-4-c500-v2-profiler is running
Tearing down inference service jic062-dpo-v1-4-c500-v2-profiler
Service jic062-dpo-v1-4-c500-v2-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.59s
Shutdown handler de-registered
jic062-dpo-v1-4-c500_v2 status is now inactive due to auto deactivation removed underperforming models