submission_id: rica40325-lora32-third-step_v6
developer_uid: rica40325
best_of: 16
celo_rating: 1255.35
display_name: rica40325-lora32-third-step_v2
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': 1.15, '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': 0.904062425844341, 'latency_mean': 1.1060608732700348, 'latency_p50': 1.1082009077072144, 'latency_p90': 1.2201647758483887}, {'batch_size': 4, 'throughput': 1.8115558068533937, 'latency_mean': 2.2029336893558504, 'latency_p50': 2.2147085666656494, 'latency_p90': 2.4627977848052978}, {'batch_size': 5, 'throughput': 1.9013693912858034, 'latency_mean': 2.613829063177109, 'latency_p50': 2.6222857236862183, 'latency_p90': 2.910688233375549}, {'batch_size': 8, 'throughput': 2.015775040661974, 'latency_mean': 3.937415528297424, 'latency_p50': 3.9228475093841553, 'latency_p90': 4.404735016822815}, {'batch_size': 10, 'throughput': 2.047224948424006, 'latency_mean': 4.824953511953354, 'latency_p50': 4.7956260442733765, 'latency_p90': 5.525885105133057}, {'batch_size': 12, 'throughput': 2.044290501128414, 'latency_mean': 5.792655689716339, 'latency_p50': 5.802775621414185, 'latency_p90': 6.580022501945495}, {'batch_size': 15, 'throughput': 2.046897089271242, 'latency_mean': 7.179496909379959, 'latency_p50': 7.247464895248413, 'latency_p90': 8.018394422531127}]
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: 19064
num_wins: 9664
ranking_group: single
status: torndown
submission_type: basic
throughput_3p7s: 2.02
timestamp: 2024-09-19T13:14:13+00:00
us_pacific_date: 2024-09-19
win_ratio: 0.5069240453210239
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-v6-mkmlizer
Waiting for job on rica40325-lora32-third-step-v6-mkmlizer to finish
rica40325-lora32-third-step-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-lora32-third-step-v6-mkmlizer: ║ _____ __ __ ║
rica40325-lora32-third-step-v6-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rica40325-lora32-third-step-v6-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rica40325-lora32-third-step-v6-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rica40325-lora32-third-step-v6-mkmlizer: ║ /___/ ║
rica40325-lora32-third-step-v6-mkmlizer: ║ ║
rica40325-lora32-third-step-v6-mkmlizer: ║ Version: 0.10.1 ║
rica40325-lora32-third-step-v6-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rica40325-lora32-third-step-v6-mkmlizer: ║ https://mk1.ai ║
rica40325-lora32-third-step-v6-mkmlizer: ║ ║
rica40325-lora32-third-step-v6-mkmlizer: ║ The license key for the current software has been verified as ║
rica40325-lora32-third-step-v6-mkmlizer: ║ belonging to: ║
rica40325-lora32-third-step-v6-mkmlizer: ║ ║
rica40325-lora32-third-step-v6-mkmlizer: ║ Chai Research Corp. ║
rica40325-lora32-third-step-v6-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rica40325-lora32-third-step-v6-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
rica40325-lora32-third-step-v6-mkmlizer: ║ ║
rica40325-lora32-third-step-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
rica40325-lora32-third-step-v6-mkmlizer: Downloaded to shared memory in 36.707s
rica40325-lora32-third-step-v6-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp10cgeh5d, device:0
rica40325-lora32-third-step-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rica40325-lora32-third-step-v6-mkmlizer: quantized model in 25.352s
rica40325-lora32-third-step-v6-mkmlizer: Processed model rica40325/lora32_third_step in 62.060s
rica40325-lora32-third-step-v6-mkmlizer: creating bucket guanaco-mkml-models
rica40325-lora32-third-step-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-lora32-third-step-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-lora32-third-step-v6
rica40325-lora32-third-step-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-lora32-third-step-v6/config.json
rica40325-lora32-third-step-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-lora32-third-step-v6/special_tokens_map.json
rica40325-lora32-third-step-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-lora32-third-step-v6/tokenizer_config.json
rica40325-lora32-third-step-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-lora32-third-step-v6/tokenizer.json
rica40325-lora32-third-step-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-lora32-third-step-v6/flywheel_model.0.safetensors
rica40325-lora32-third-step-v6-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%|▏ | 4/291 [00:00<00:07, 37.90it/s] Loading 0: 5%|▌ | 16/291 [00:00<00:03, 69.81it/s] Loading 0: 11%|█ | 31/291 [00:00<00:02, 88.75it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:02, 88.31it/s] Loading 0: 18%|█▊ | 52/291 [00:00<00:02, 86.43it/s] Loading 0: 21%|██ | 61/291 [00:00<00:02, 82.41it/s] Loading 0: 24%|██▍ | 71/291 [00:00<00:02, 87.27it/s] Loading 0: 27%|██▋ | 80/291 [00:00<00:02, 84.22it/s] Loading 0: 31%|███ | 89/291 [00:02<00:08, 22.57it/s] Loading 0: 33%|███▎ | 97/291 [00:02<00:07, 27.54it/s] Loading 0: 38%|███▊ | 112/291 [00:02<00:04, 40.21it/s] Loading 0: 43%|████▎ | 124/291 [00:02<00:03, 48.89it/s] Loading 0: 48%|████▊ | 139/291 [00:02<00:02, 60.71it/s] Loading 0: 52%|█████▏ | 151/291 [00:02<00:02, 66.87it/s] Loading 0: 55%|█████▍ | 160/291 [00:02<00:01, 68.56it/s] Loading 0: 58%|█████▊ | 169/291 [00:02<00:01, 72.15it/s] Loading 0: 61%|██████ | 178/291 [00:03<00:01, 72.57it/s] Loading 0: 64%|██████▍ | 187/291 [00:04<00:04, 23.56it/s] Loading 0: 67%|██████▋ | 196/291 [00:04<00:03, 29.66it/s] Loading 0: 70%|███████ | 205/291 [00:04<00:02, 35.93it/s] Loading 0: 74%|███████▎ | 214/291 [00:04<00:01, 43.54it/s] Loading 0: 77%|███████▋ | 223/291 [00:04<00:01, 49.37it/s] Loading 0: 80%|███████▉ | 232/291 [00:04<00:01, 55.63it/s] Loading 0: 83%|████████▎ | 241/291 [00:04<00:00, 59.12it/s] Loading 0: 86%|████████▌ | 250/291 [00:04<00:00, 63.53it/s] Loading 0: 89%|████████▉ | 259/291 [00:05<00:00, 66.73it/s] Loading 0: 92%|█████████▏| 268/291 [00:05<00:00, 67.91it/s] Loading 0: 97%|█████████▋| 283/291 [00:05<00:00, 79.52it/s]
Job rica40325-lora32-third-step-v6-mkmlizer completed after 84.6s with status: succeeded
Stopping job with name rica40325-lora32-third-step-v6-mkmlizer
Pipeline stage MKMLizer completed in 86.75s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rica40325-lora32-third-step-v6
Waiting for inference service rica40325-lora32-third-step-v6 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service rica40325-lora32-third-step-v6 ready after 201.0653748512268s
Pipeline stage MKMLDeployer completed in 202.25s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.17981219291687s
Received healthy response to inference request in 1.7679500579833984s
Received healthy response to inference request in 3.03170108795166s
Received healthy response to inference request in 1.82501220703125s
Received healthy response to inference request in 1.6783623695373535s
5 requests
0 failed requests
5th percentile: 1.6962799072265624
10th percentile: 1.7141974449157715
20th percentile: 1.7500325202941895
30th percentile: 1.7793624877929688
40th percentile: 1.8021873474121093
50th percentile: 1.82501220703125
60th percentile: 2.307687759399414
70th percentile: 2.790363311767578
80th percentile: 3.061323308944702
90th percentile: 3.1205677509307863
95th percentile: 3.150189971923828
99th percentile: 3.1738877487182617
mean time: 2.2965675830841064
Pipeline stage StressChecker completed in 12.57s
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 6.14s
Shutdown handler de-registered
rica40325-lora32-third-step_v6 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 rica40325-lora32-third-step-v6-profiler
Waiting for inference service rica40325-lora32-third-step-v6-profiler to be ready
Inference service rica40325-lora32-third-step-v6-profiler ready after 200.4712061882019s
Pipeline stage MKMLProfilerDeployer completed in 200.83s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rica40325-lora32-thia9976b6f719da39cc244a69d33a88a37-deplorwkxv:/code/chaiverse_profiler_1726752209 --namespace tenant-chaiml-guanaco
kubectl exec -it rica40325-lora32-thia9976b6f719da39cc244a69d33a88a37-deplorwkxv --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726752209 && 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_1726752209/summary.json'
kubectl exec -it rica40325-lora32-thia9976b6f719da39cc244a69d33a88a37-deplorwkxv --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726752209/summary.json'
Pipeline stage MKMLProfilerRunner completed in 835.25s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rica40325-lora32-third-step-v6-profiler is running
Tearing down inference service rica40325-lora32-third-step-v6-profiler
Service rica40325-lora32-third-step-v6-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.12s
Shutdown handler de-registered
rica40325-lora32-third-step_v6 status is now inactive due to auto deactivation removed underperforming models
rica40325-lora32-third-step_v6 status is now torndown due to DeploymentManager action