submission_id: rica40325-9-15-sftdpo_v8
developer_uid: rica40325
best_of: 16
celo_rating: 1265.99
display_name: rica40325-9-15-sftdpo_v1
family_friendly_score: 0.0
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{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'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: False
language_model: rica40325/9-15-sftdpo
latencies: [{'batch_size': 1, 'throughput': 0.9163592869855016, 'latency_mean': 1.091185051202774, 'latency_p50': 1.0827306509017944, 'latency_p90': 1.2282312154769897}, {'batch_size': 4, 'throughput': 1.8287377223921144, 'latency_mean': 2.1780820405483245, 'latency_p50': 2.166540265083313, 'latency_p90': 2.4343494415283202}, {'batch_size': 5, 'throughput': 1.8943301442635156, 'latency_mean': 2.630121718645096, 'latency_p50': 2.6370925903320312, 'latency_p90': 2.91186945438385}, {'batch_size': 8, 'throughput': 2.014998123614956, 'latency_mean': 3.938282861709595, 'latency_p50': 3.946722149848938, 'latency_p90': 4.4760830163955685}, {'batch_size': 10, 'throughput': 2.0293677189946493, 'latency_mean': 4.884959107637405, 'latency_p50': 4.851858973503113, 'latency_p90': 5.690195226669311}, {'batch_size': 12, 'throughput': 2.033108093741409, 'latency_mean': 5.831200689077377, 'latency_p50': 5.806869029998779, 'latency_p90': 6.899230027198791}, {'batch_size': 15, 'throughput': 2.061762176960024, 'latency_mean': 7.125559293031692, 'latency_p50': 7.231380224227905, 'latency_p90': 7.980415320396423}]
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: rica40325/9-15-sftdpo
model_name: rica40325-9-15-sftdpo_v1
model_num_parameters: 8030261248.0
model_repo: rica40325/9-15-sftdpo
model_size: 8B
num_battles: 366205
num_wins: 192738
ranking_group: single
status: torndown
submission_type: basic
throughput_3p7s: 2.01
timestamp: 2024-09-21T10:09:45+00:00
us_pacific_date: 2024-09-21
win_ratio: 0.5263117652680875
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 rica40325-9-15-sftdpo-v8-mkmlizer
Waiting for job on rica40325-9-15-sftdpo-v8-mkmlizer to finish
rica40325-9-15-sftdpo-v8-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-9-15-sftdpo-v8-mkmlizer: ║     _____            __           __                                ║
rica40325-9-15-sftdpo-v8-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rica40325-9-15-sftdpo-v8-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rica40325-9-15-sftdpo-v8-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rica40325-9-15-sftdpo-v8-mkmlizer: ║       /___/                                                         ║
rica40325-9-15-sftdpo-v8-mkmlizer: ║                                                                     ║
rica40325-9-15-sftdpo-v8-mkmlizer: ║  Version: 0.10.1                                                    ║
rica40325-9-15-sftdpo-v8-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rica40325-9-15-sftdpo-v8-mkmlizer: ║  https://mk1.ai                                                     ║
rica40325-9-15-sftdpo-v8-mkmlizer: ║                                                                     ║
rica40325-9-15-sftdpo-v8-mkmlizer: ║  The license key for the current software has been verified as      ║
rica40325-9-15-sftdpo-v8-mkmlizer: ║  belonging to:                                                      ║
rica40325-9-15-sftdpo-v8-mkmlizer: ║                                                                     ║
rica40325-9-15-sftdpo-v8-mkmlizer: ║  Chai Research Corp.                                                ║
rica40325-9-15-sftdpo-v8-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rica40325-9-15-sftdpo-v8-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
rica40325-9-15-sftdpo-v8-mkmlizer: ║                                                                     ║
rica40325-9-15-sftdpo-v8-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rica40325-9-15-sftdpo-v8-mkmlizer: Downloaded to shared memory in 20.336s
rica40325-9-15-sftdpo-v8-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpqv1_jqyp, device:0
rica40325-9-15-sftdpo-v8-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rica40325-9-15-sftdpo-v8-mkmlizer: quantized model in 25.326s
rica40325-9-15-sftdpo-v8-mkmlizer: Processed model rica40325/9-15-sftdpo in 45.662s
rica40325-9-15-sftdpo-v8-mkmlizer: creating bucket guanaco-mkml-models
rica40325-9-15-sftdpo-v8-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-9-15-sftdpo-v8-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-9-15-sftdpo-v8
rica40325-9-15-sftdpo-v8-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-9-15-sftdpo-v8/special_tokens_map.json
rica40325-9-15-sftdpo-v8-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-9-15-sftdpo-v8/config.json
rica40325-9-15-sftdpo-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-9-15-sftdpo-v8/tokenizer_config.json
rica40325-9-15-sftdpo-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-9-15-sftdpo-v8/tokenizer.json
rica40325-9-15-sftdpo-v8-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-9-15-sftdpo-v8/flywheel_model.0.safetensors
rica40325-9-15-sftdpo-v8-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 4/291 [00:00<00:07, 38.66it/s]
Loading 0:   5%|▌         | 15/291 [00:00<00:03, 80.01it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:03, 80.12it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:02, 95.35it/s]
Loading 0:  17%|█▋        | 50/291 [00:00<00:02, 93.53it/s]
Loading 0:  21%|██        | 61/291 [00:00<00:02, 84.33it/s]
Loading 0:  24%|██▍       | 70/291 [00:00<00:02, 83.43it/s]
Loading 0:  29%|██▊       | 83/291 [00:01<00:08, 24.75it/s]
Loading 0:  31%|███       | 90/291 [00:02<00:07, 28.56it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:04, 39.05it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:03, 48.30it/s]
Loading 0:  43%|████▎     | 124/291 [00:02<00:03, 54.67it/s]
Loading 0:  48%|████▊     | 139/291 [00:02<00:02, 68.84it/s]
Loading 0:  52%|█████▏    | 151/291 [00:02<00:01, 75.35it/s]
Loading 0:  57%|█████▋    | 166/291 [00:02<00:01, 86.19it/s]
Loading 0:  61%|██████    | 178/291 [00:02<00:01, 86.49it/s]
Loading 0:  65%|██████▍   | 188/291 [00:04<00:03, 27.47it/s]
Loading 0:  69%|██████▉   | 202/291 [00:04<00:02, 36.60it/s]
Loading 0:  74%|███████▎  | 214/291 [00:04<00:01, 44.35it/s]
Loading 0:  79%|███████▊  | 229/291 [00:04<00:01, 55.64it/s]
Loading 0:  82%|████████▏ | 239/291 [00:04<00:00, 60.96it/s]
Loading 0:  86%|████████▌ | 250/291 [00:04<00:00, 65.58it/s]
Loading 0:  91%|█████████ | 265/291 [00:04<00:00, 77.76it/s]
Loading 0:  95%|█████████▌| 277/291 [00:04<00:00, 82.26it/s]
Loading 0:  99%|█████████▊| 287/291 [00:05<00:00, 50.53it/s]
                                                            

Job rica40325-9-15-sftdpo-v8-mkmlizer completed after 74.81s with status: succeeded
Stopping job with name rica40325-9-15-sftdpo-v8-mkmlizer
Pipeline stage MKMLizer completed in 80.35s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rica40325-9-15-sftdpo-v8
Waiting for inference service rica40325-9-15-sftdpo-v8 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
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
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
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
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
Inference service rica40325-9-15-sftdpo-v8 ready after 191.59439039230347s
Pipeline stage MKMLDeployer completed in 192.13s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.944368600845337s
Received healthy response to inference request in 1.6274137496948242s
Received healthy response to inference request in 2.127457857131958s
Received healthy response to inference request in 1.456352710723877s
Received healthy response to inference request in 1.881209135055542s
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
5 requests
0 failed requests
5th percentile: 1.4905649185180665
10th percentile: 1.5247771263122558
20th percentile: 1.5932015419006347
30th percentile: 1.6781728267669678
40th percentile: 1.7796909809112549
50th percentile: 1.881209135055542
60th percentile: 1.90647292137146
70th percentile: 1.931736707687378
80th percentile: 1.9809864521026612
90th percentile: 2.0542221546173094
95th percentile: 2.0908400058746337
99th percentile: 2.1201342868804933
mean time: 1.8073604106903076
Pipeline stage StressChecker completed in 15.24s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%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
Pipeline stage TriggerMKMLProfilingPipeline completed in 4.84s
Shutdown handler de-registered
rica40325-9-15-sftdpo_v8 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 0.22s
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 rica40325-9-15-sftdpo-v8-profiler
Waiting for inference service rica40325-9-15-sftdpo-v8-profiler to be ready
Inference service rica40325-9-15-sftdpo-v8-profiler ready after 190.45086097717285s
Pipeline stage MKMLProfilerDeployer completed in 190.82s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rica40325-9-15-sftdpo-v8-profiler-predictor-00001-deploymep5kmx:/code/chaiverse_profiler_1726913917 --namespace tenant-chaiml-guanaco
kubectl exec -it rica40325-9-15-sftdpo-v8-profiler-predictor-00001-deploymep5kmx --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726913917 && 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_1726913917/summary.json'
kubectl exec -it rica40325-9-15-sftdpo-v8-profiler-predictor-00001-deploymep5kmx --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726913917/summary.json'
Pipeline stage MKMLProfilerRunner completed in 834.38s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rica40325-9-15-sftdpo-v8-profiler is running
Tearing down inference service rica40325-9-15-sftdpo-v8-profiler
Service rica40325-9-15-sftdpo-v8-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.13s
Shutdown handler de-registered
rica40325-9-15-sftdpo_v8 status is now inactive due to auto deactivation removed underperforming models
rica40325-9-15-sftdpo_v8 status is now torndown due to DeploymentManager action