submission_id: rica40325-lora32-third-step_v5
developer_uid: rica40325
alignment_samples: 12191
alignment_score: 0.2936716738358408
best_of: 16
celo_rating: 1254.72
display_name: rica40325-lora32-third-step_v2
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': 1.15, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, '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/lora32_third_step
latencies: [{'batch_size': 1, 'throughput': 0.9151423655944816, 'latency_mean': 1.092667589187622, 'latency_p50': 1.0944503545761108, 'latency_p90': 1.2223295211791991}, {'batch_size': 4, 'throughput': 1.7985631054077684, 'latency_mean': 2.2135909175872803, 'latency_p50': 2.244563579559326, 'latency_p90': 2.4717017889022825}, {'batch_size': 5, 'throughput': 1.9252793300256488, 'latency_mean': 2.5864245820045473, 'latency_p50': 2.6094610691070557, 'latency_p90': 2.881533455848694}, {'batch_size': 8, 'throughput': 2.0451326202120717, 'latency_mean': 3.8896944451332094, 'latency_p50': 3.901007652282715, 'latency_p90': 4.349753212928772}, {'batch_size': 10, 'throughput': 2.0689926990174676, 'latency_mean': 4.786376857757569, 'latency_p50': 4.762217879295349, 'latency_p90': 5.533208656311035}, {'batch_size': 12, 'throughput': 2.0435422839155977, 'latency_mean': 5.794221022129059, 'latency_p50': 5.830098986625671, 'latency_p90': 6.643158411979675}, {'batch_size': 15, 'throughput': 2.068250066742336, 'latency_mean': 7.107808477878571, 'latency_p50': 7.172149896621704, 'latency_p90': 7.920443820953369}]
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: rica40325/lora32_third_s
model_name: rica40325-lora32-third-step_v2
model_num_parameters: 8030261248.0
model_repo: rica40325/lora32_third_step
model_size: 8B
num_battles: 12191
num_wins: 6343
propriety_score: 0.7263875365141188
propriety_total_count: 1027.0
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 2.04
timestamp: 2024-09-05T08:03:23+00:00
us_pacific_date: 2024-09-05
win_ratio: 0.5203018620293659
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-lora32-third-step-v5-mkmlizer
Waiting for job on rica40325-lora32-third-step-v5-mkmlizer to finish
rica40325-lora32-third-step-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-lora32-third-step-v5-mkmlizer: ║     _____            __           __                                ║
rica40325-lora32-third-step-v5-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rica40325-lora32-third-step-v5-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rica40325-lora32-third-step-v5-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rica40325-lora32-third-step-v5-mkmlizer: ║       /___/                                                         ║
rica40325-lora32-third-step-v5-mkmlizer: ║                                                                     ║
rica40325-lora32-third-step-v5-mkmlizer: ║  Version: 0.10.1                                                    ║
rica40325-lora32-third-step-v5-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rica40325-lora32-third-step-v5-mkmlizer: ║  https://mk1.ai                                                     ║
rica40325-lora32-third-step-v5-mkmlizer: ║                                                                     ║
rica40325-lora32-third-step-v5-mkmlizer: ║  The license key for the current software has been verified as      ║
rica40325-lora32-third-step-v5-mkmlizer: ║  belonging to:                                                      ║
rica40325-lora32-third-step-v5-mkmlizer: ║                                                                     ║
rica40325-lora32-third-step-v5-mkmlizer: ║  Chai Research Corp.                                                ║
rica40325-lora32-third-step-v5-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rica40325-lora32-third-step-v5-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
rica40325-lora32-third-step-v5-mkmlizer: ║                                                                     ║
rica40325-lora32-third-step-v5-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
rica40325-lora32-third-step-v5-mkmlizer: Downloaded to shared memory in 36.618s
rica40325-lora32-third-step-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpsggj3099, device:0
rica40325-lora32-third-step-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rica40325-lora32-third-step-v5-mkmlizer: quantized model in 26.754s
rica40325-lora32-third-step-v5-mkmlizer: Processed model rica40325/lora32_third_step in 63.372s
rica40325-lora32-third-step-v5-mkmlizer: creating bucket guanaco-mkml-models
rica40325-lora32-third-step-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-lora32-third-step-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-lora32-third-step-v5
rica40325-lora32-third-step-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-lora32-third-step-v5/special_tokens_map.json
rica40325-lora32-third-step-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-lora32-third-step-v5/config.json
rica40325-lora32-third-step-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-lora32-third-step-v5/tokenizer_config.json
rica40325-lora32-third-step-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-lora32-third-step-v5/tokenizer.json
rica40325-lora32-third-step-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-lora32-third-step-v5/flywheel_model.0.safetensors
rica40325-lora32-third-step-v5-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 4/291 [00:00<00:09, 30.25it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:04, 58.48it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:03, 72.07it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:02, 86.50it/s]
Loading 0:  18%|█▊        | 52/291 [00:00<00:02, 84.10it/s]
Loading 0:  21%|██        | 61/291 [00:00<00:02, 78.64it/s]
Loading 0:  24%|██▍       | 70/291 [00:00<00:02, 78.75it/s]
Loading 0:  27%|██▋       | 80/291 [00:01<00:02, 84.25it/s]
Loading 0:  31%|███       | 89/291 [00:02<00:09, 20.65it/s]
Loading 0:  33%|███▎      | 97/291 [00:02<00:07, 25.64it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:04, 37.40it/s]
Loading 0:  42%|████▏     | 123/291 [00:02<00:03, 46.75it/s]
Loading 0:  46%|████▌     | 133/291 [00:02<00:03, 51.93it/s]
Loading 0:  49%|████▉     | 142/291 [00:02<00:02, 57.20it/s]
Loading 0:  52%|█████▏    | 151/291 [00:02<00:02, 61.32it/s]
Loading 0:  55%|█████▍    | 160/291 [00:03<00:02, 62.54it/s]
Loading 0:  58%|█████▊    | 169/291 [00:03<00:01, 68.18it/s]
Loading 0:  63%|██████▎   | 184/291 [00:03<00:01, 79.86it/s]
Loading 0:  66%|██████▋   | 193/291 [00:04<00:04, 22.05it/s]
Loading 0:  69%|██████▉   | 202/291 [00:04<00:03, 27.51it/s]
Loading 0:  73%|███████▎  | 213/291 [00:04<00:02, 36.17it/s]
Loading 0:  76%|███████▋  | 222/291 [00:04<00:01, 42.94it/s]
Loading 0:  80%|███████▉  | 232/291 [00:05<00:01, 48.44it/s]
Loading 0:  85%|████████▍ | 247/291 [00:05<00:00, 61.03it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 64.34it/s]
Loading 0:  91%|█████████ | 265/291 [00:05<00:00, 65.74it/s]
Loading 0:  94%|█████████▍| 274/291 [00:05<00:00, 69.03it/s]
Loading 0:  97%|█████████▋| 283/291 [00:05<00:00, 70.42it/s]
Loading 0: 100%|██████████| 291/291 [00:11<00:00,  5.25it/s]
                                                            

Job rica40325-lora32-third-step-v5-mkmlizer completed after 93.96s with status: succeeded
Stopping job with name rica40325-lora32-third-step-v5-mkmlizer
Pipeline stage MKMLizer completed in 94.86s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rica40325-lora32-third-step-v5
Waiting for inference service rica40325-lora32-third-step-v5 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
Inference service rica40325-lora32-third-step-v5 ready after 140.98420333862305s
Pipeline stage MKMLDeployer completed in 141.37s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.15454363822937s
Received healthy response to inference request in 1.6412534713745117s
Received healthy response to inference request in 2.0561683177948s
Received healthy response to inference request in 1.9012622833251953s
Received healthy response to inference request in 1.4248723983764648s
5 requests
0 failed requests
5th percentile: 1.4681486129760741
10th percentile: 1.5114248275756836
20th percentile: 1.5979772567749024
30th percentile: 1.6932552337646485
40th percentile: 1.7972587585449218
50th percentile: 1.9012622833251953
60th percentile: 1.9632246971130372
70th percentile: 2.025187110900879
80th percentile: 2.0758433818817137
90th percentile: 2.115193510055542
95th percentile: 2.1348685741424562
99th percentile: 2.150608625411987
mean time: 1.8356200218200684
Pipeline stage StressChecker completed in 10.08s
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 9.35s
Shutdown handler de-registered
rica40325-lora32-third-step_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 0.11s
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-lora32-third-step-v5-profiler
Waiting for inference service rica40325-lora32-third-step-v5-profiler to be ready
Inference service rica40325-lora32-third-step-v5-profiler ready after 140.32315063476562s
Pipeline stage MKMLProfilerDeployer completed in 140.69s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rica40325-lora32-thi2fecb6ccf25d8a507df26d9cb8a79ef3-deploxkstg:/code/chaiverse_profiler_1725523838 --namespace tenant-chaiml-guanaco
kubectl exec -it rica40325-lora32-thi2fecb6ccf25d8a507df26d9cb8a79ef3-deploxkstg --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725523838 && 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_1725523838/summary.json'
kubectl exec -it rica40325-lora32-thi2fecb6ccf25d8a507df26d9cb8a79ef3-deploxkstg --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725523838/summary.json'
Pipeline stage MKMLProfilerRunner completed in 828.51s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rica40325-lora32-third-step-v5-profiler is running
Tearing down inference service rica40325-lora32-third-step-v5-profiler
Service rica40325-lora32-third-step-v5-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.67s
Shutdown handler de-registered
rica40325-lora32-third-step_v5 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics