submission_id: chaiml-elite-feed-convo-_7085_v3
developer_uid: zonemercy
alignment_samples: 13258
alignment_score: 0.5206472126411347
best_of: 8
celo_rating: 1253.65
display_name: chaiml-elite-feed-convo-_7085_v3
formatter: {'memory_template': "Bot's name:{bot_name}\n####\n", 'prompt_template': '', 'bot_template': 'Bot: {message}</s>', 'user_template': 'User: {message}</s>', 'response_template': 'Bot:', 'truncate_by_message': True}
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': ['</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/Elite-Feed-Convo-v2-1e5ep2
latencies: [{'batch_size': 1, 'throughput': 0.6085286902665145, 'latency_mean': 1.6432468235492705, 'latency_p50': 1.6423653364181519, 'latency_p90': 1.8066828012466432}, {'batch_size': 3, 'throughput': 1.0699317289798502, 'latency_mean': 2.797241563796997, 'latency_p50': 2.7996426820755005, 'latency_p90': 3.064992308616638}, {'batch_size': 5, 'throughput': 1.2031594478574232, 'latency_mean': 4.144540500640869, 'latency_p50': 4.162484049797058, 'latency_p90': 4.6096041917800905}, {'batch_size': 6, 'throughput': 1.2392866170383419, 'latency_mean': 4.816020349264145, 'latency_p50': 4.815735220909119, 'latency_p90': 5.4103713750839235}, {'batch_size': 8, 'throughput': 1.2285977468951272, 'latency_mean': 6.474063066244125, 'latency_p50': 6.531718015670776, 'latency_p90': 7.286085557937621}, {'batch_size': 10, 'throughput': 1.188514849293426, 'latency_mean': 8.361175886392594, 'latency_p50': 8.430795431137085, 'latency_p90': 9.409000086784362}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: ChaiML/Elite-Feed-Convo-
model_name: chaiml-elite-feed-convo-_7085_v3
model_num_parameters: 12772070400.0
model_repo: ChaiML/Elite-Feed-Convo-v2-1e5ep2
model_size: 13B
num_battles: 13258
num_wins: 6855
propriety_score: 0.7310098302055407
propriety_total_count: 1119.0
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 1.17
timestamp: 2024-09-12T19:51:08+00:00
us_pacific_date: 2024-09-12
win_ratio: 0.517046311660884
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-elite-feed-convo-7085-v3-mkmlizer
Waiting for job on chaiml-elite-feed-convo-7085-v3-mkmlizer to finish
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-elite-feed-convo-7085-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-elite-feed-convo-7085-v3-mkmlizer: ║     _____            __           __                                ║
chaiml-elite-feed-convo-7085-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-elite-feed-convo-7085-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-elite-feed-convo-7085-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-elite-feed-convo-7085-v3-mkmlizer: ║       /___/                                                         ║
chaiml-elite-feed-convo-7085-v3-mkmlizer: ║                                                                     ║
chaiml-elite-feed-convo-7085-v3-mkmlizer: ║  Version: 0.10.1                                                    ║
chaiml-elite-feed-convo-7085-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-elite-feed-convo-7085-v3-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-elite-feed-convo-7085-v3-mkmlizer: ║                                                                     ║
chaiml-elite-feed-convo-7085-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-elite-feed-convo-7085-v3-mkmlizer: ║  belonging to:                                                      ║
chaiml-elite-feed-convo-7085-v3-mkmlizer: ║                                                                     ║
chaiml-elite-feed-convo-7085-v3-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-elite-feed-convo-7085-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-elite-feed-convo-7085-v3-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-elite-feed-convo-7085-v3-mkmlizer: ║                                                                     ║
chaiml-elite-feed-convo-7085-v3-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
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
chaiml-elite-feed-convo-7085-v3-mkmlizer: Downloaded to shared memory in 57.228s
chaiml-elite-feed-convo-7085-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpiw6af5f3, device:0
chaiml-elite-feed-convo-7085-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-elite-feed-convo-7085-v3-mkmlizer: quantized model in 39.670s
chaiml-elite-feed-convo-7085-v3-mkmlizer: Processed model ChaiML/Elite-Feed-Convo-v2-1e5ep2 in 96.898s
chaiml-elite-feed-convo-7085-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-elite-feed-convo-7085-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-elite-feed-convo-7085-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-elite-feed-convo-7085-v3
chaiml-elite-feed-convo-7085-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-elite-feed-convo-7085-v3/config.json
chaiml-elite-feed-convo-7085-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-elite-feed-convo-7085-v3/special_tokens_map.json
chaiml-elite-feed-convo-7085-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-elite-feed-convo-7085-v3/tokenizer_config.json
chaiml-elite-feed-convo-7085-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-elite-feed-convo-7085-v3/tokenizer.json
Job chaiml-elite-feed-convo-7085-v3-mkmlizer completed after 127.44s with status: succeeded
Stopping job with name chaiml-elite-feed-convo-7085-v3-mkmlizer
Pipeline stage MKMLizer completed in 128.16s
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 chaiml-elite-feed-convo-7085-v3
Waiting for inference service chaiml-elite-feed-convo-7085-v3 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_jugel_2024-09-09: ('http://chaiml-llama-8b-pairwis-8189-v19-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '{"error":"ValueError : [TypeError(\\"\'numpy.int64\' object is not iterable\\"), TypeError(\'vars() argument must have __dict__ attribute\')]"}')
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 chaiml-elite-feed-convo-7085-v3 ready after 172.7350926399231s
Pipeline stage MKMLDeployer completed in 175.26s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.0102217197418213s
Received healthy response to inference request in 1.9510715007781982s
Received healthy response to inference request in 2.832263231277466s
Received healthy response to inference request in 2.145969867706299s
Received healthy response to inference request in 2.0692543983459473s
5 requests
0 failed requests
5th percentile: 1.974708080291748
10th percentile: 1.9983446598052979
20th percentile: 2.0456178188323975
30th percentile: 2.0845974922180175
40th percentile: 2.1152836799621584
50th percentile: 2.145969867706299
60th percentile: 2.4204872131347654
70th percentile: 2.695004558563232
80th percentile: 2.867854928970337
90th percentile: 2.939038324356079
95th percentile: 2.97463002204895
99th percentile: 3.003103380203247
mean time: 2.4017561435699464
Pipeline stage StressChecker completed in 14.18s
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 5.69s
Shutdown handler de-registered
chaiml-elite-feed-convo-_7085_v3 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 chaiml-elite-feed-convo-7085-v3-profiler
Waiting for inference service chaiml-elite-feed-convo-7085-v3-profiler to be ready
Inference service chaiml-elite-feed-convo-7085-v3-profiler ready after 170.44930386543274s
Pipeline stage MKMLProfilerDeployer completed in 170.84s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-elite-feed-coc4481ed89b09f6916c15b06ad975fb19-deplowpl4b:/code/chaiverse_profiler_1726171204 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-elite-feed-coc4481ed89b09f6916c15b06ad975fb19-deplowpl4b --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726171204 && 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_1726171204/summary.json'
kubectl exec -it chaiml-elite-feed-coc4481ed89b09f6916c15b06ad975fb19-deplowpl4b --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726171204/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1181.32s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-elite-feed-convo-7085-v3-profiler is running
Tearing down inference service chaiml-elite-feed-convo-7085-v3-profiler
Service chaiml-elite-feed-convo-7085-v3-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.76s
Shutdown handler de-registered
chaiml-elite-feed-convo-_7085_v3 status is now inactive due to auto deactivation removed underperforming models