developer_uid: sanchuanhehe
submission_id: sanchuanhehe-adjusted-co_1115_v1
model_name: sanchuanhehe-adjusted-co_1115_v1
model_group: sanchuanhehe/adjusted_co
status: torndown
timestamp: 2024-09-17T13:11:18+00:00
num_battles: 11071
num_wins: 4555
celo_rating: 1113.07
family_friendly_score: 0.0
submission_type: basic
model_repo: sanchuanhehe/adjusted_config_19_l
model_architecture: MistralForCausalLM
model_num_parameters: 7241732096.0
best_of: 1
max_input_tokens: 512
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 1.1266537831656493, 'latency_mean': 0.8875253379344941, 'latency_p50': 0.8859624862670898, 'latency_p90': 0.9857531785964966}, {'batch_size': 5, 'throughput': 3.6803011120995417, 'latency_mean': 1.3515129697322845, 'latency_p50': 1.340242862701416, 'latency_p90': 1.5032732248306273}, {'batch_size': 10, 'throughput': 5.4197366078746905, 'latency_mean': 1.812689243555069, 'latency_p50': 1.7991713285446167, 'latency_p90': 2.0681201457977294}, {'batch_size': 15, 'throughput': 6.403111863904806, 'latency_mean': 2.3023937821388243, 'latency_p50': 2.31720769405365, 'latency_p90': 2.634665870666504}, {'batch_size': 20, 'throughput': 6.891003617950066, 'latency_mean': 2.8459349703788757, 'latency_p50': 2.880486845970154, 'latency_p90': 3.2404928922653196}, {'batch_size': 25, 'throughput': 7.3363447072979575, 'latency_mean': 3.340873305797577, 'latency_p50': 3.3450982570648193, 'latency_p90': 3.8709010601043703}, {'batch_size': 30, 'throughput': 7.601021815716434, 'latency_mean': 3.849526598453522, 'latency_p50': 3.7661314010620117, 'latency_p90': 4.420961380004883}, {'batch_size': 35, 'throughput': 7.740376257627704, 'latency_mean': 4.400445355176926, 'latency_p50': 4.367812514305115, 'latency_p90': 5.2420347929000854}, {'batch_size': 40, 'throughput': 7.730907535389102, 'latency_mean': 5.0076210808753965, 'latency_p50': 4.928338050842285, 'latency_p90': 5.883728384971618}, {'batch_size': 45, 'throughput': 7.77036338840505, 'latency_mean': 5.557050169706344, 'latency_p50': 5.545403957366943, 'latency_p90': 6.414886617660522}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: sanchuanhehe-adjusted-co_1115_v1
is_internal_developer: False
language_model: sanchuanhehe/adjusted_config_19_l
model_size: 7B
ranking_group: single
throughput_3p7s: 7.71
us_pacific_date: 2024-09-17
win_ratio: 0.41143528136573027
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': 1, 'max_output_tokens': 64}
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}
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 sanchuanhehe-adjusted-co-1115-v1-mkmlizer
Waiting for job on sanchuanhehe-adjusted-co-1115-v1-mkmlizer to finish
sanchuanhehe-adjusted-co-1115-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sanchuanhehe-adjusted-co-1115-v1-mkmlizer: ║ _____ __ __ ║
sanchuanhehe-adjusted-co-1115-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
sanchuanhehe-adjusted-co-1115-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
sanchuanhehe-adjusted-co-1115-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
sanchuanhehe-adjusted-co-1115-v1-mkmlizer: ║ /___/ ║
sanchuanhehe-adjusted-co-1115-v1-mkmlizer: ║ ║
sanchuanhehe-adjusted-co-1115-v1-mkmlizer: ║ Version: 0.10.1 ║
sanchuanhehe-adjusted-co-1115-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
sanchuanhehe-adjusted-co-1115-v1-mkmlizer: ║ https://mk1.ai ║
sanchuanhehe-adjusted-co-1115-v1-mkmlizer: ║ ║
sanchuanhehe-adjusted-co-1115-v1-mkmlizer: ║ The license key for the current software has been verified as ║
sanchuanhehe-adjusted-co-1115-v1-mkmlizer: ║ belonging to: ║
sanchuanhehe-adjusted-co-1115-v1-mkmlizer: ║ ║
sanchuanhehe-adjusted-co-1115-v1-mkmlizer: ║ Chai Research Corp. ║
sanchuanhehe-adjusted-co-1115-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
sanchuanhehe-adjusted-co-1115-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
sanchuanhehe-adjusted-co-1115-v1-mkmlizer: ║ ║
sanchuanhehe-adjusted-co-1115-v1-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
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
sanchuanhehe-adjusted-co-1115-v1-mkmlizer: Downloaded to shared memory in 31.570s
sanchuanhehe-adjusted-co-1115-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp0bd2xvts, device:0
sanchuanhehe-adjusted-co-1115-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sanchuanhehe-adjusted-co-1115-v1-mkmlizer: quantized model in 18.693s
sanchuanhehe-adjusted-co-1115-v1-mkmlizer: Processed model sanchuanhehe/adjusted_config_19_l in 50.263s
sanchuanhehe-adjusted-co-1115-v1-mkmlizer: creating bucket guanaco-mkml-models
sanchuanhehe-adjusted-co-1115-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sanchuanhehe-adjusted-co-1115-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-1115-v1
sanchuanhehe-adjusted-co-1115-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-1115-v1/config.json
sanchuanhehe-adjusted-co-1115-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-1115-v1/special_tokens_map.json
sanchuanhehe-adjusted-co-1115-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-1115-v1/tokenizer_config.json
sanchuanhehe-adjusted-co-1115-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-1115-v1/tokenizer.model
sanchuanhehe-adjusted-co-1115-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-1115-v1/tokenizer.json
sanchuanhehe-adjusted-co-1115-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-1115-v1/flywheel_model.0.safetensors
sanchuanhehe-adjusted-co-1115-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 7/291 [00:00<00:05, 52.72it/s] Loading 0: 6%|▌ | 17/291 [00:00<00:03, 75.68it/s] Loading 0: 9%|▊ | 25/291 [00:00<00:03, 69.37it/s] Loading 0: 12%|█▏ | 34/291 [00:00<00:03, 72.05it/s] Loading 0: 15%|█▍ | 43/291 [00:00<00:03, 73.86it/s] Loading 0: 18%|█▊ | 52/291 [00:00<00:03, 74.69it/s] Loading 0: 21%|██ | 61/291 [00:00<00:03, 76.65it/s] Loading 0: 24%|██▍ | 70/291 [00:00<00:03, 70.94it/s] Loading 0: 27%|██▋ | 79/291 [00:01<00:03, 69.32it/s] Loading 0: 30%|███ | 88/291 [00:01<00:03, 64.31it/s] Loading 0: 33%|███▎ | 97/291 [00:01<00:03, 60.40it/s] Loading 0: 36%|███▌ | 104/291 [00:02<00:10, 18.69it/s] Loading 0: 38%|███▊ | 112/291 [00:02<00:07, 23.17it/s] Loading 0: 42%|████▏ | 121/291 [00:02<00:05, 28.70it/s] Loading 0: 45%|████▍ | 130/291 [00:03<00:04, 33.99it/s] Loading 0: 48%|████▊ | 139/291 [00:03<00:03, 38.24it/s] Loading 0: 51%|█████ | 148/291 [00:03<00:03, 42.14it/s] Loading 0: 54%|█████▍ | 157/291 [00:03<00:02, 46.53it/s] Loading 0: 57%|█████▋ | 166/291 [00:03<00:02, 49.43it/s] Loading 0: 60%|██████ | 175/291 [00:03<00:02, 51.63it/s] Loading 0: 63%|██████▎ | 184/291 [00:03<00:01, 54.49it/s] Loading 0: 66%|██████▋ | 193/291 [00:04<00:01, 56.22it/s] Loading 0: 69%|██████▉ | 202/291 [00:04<00:01, 58.57it/s] Loading 0: 72%|███████▏ | 209/291 [00:05<00:04, 19.71it/s] Loading 0: 74%|███████▎ | 214/291 [00:05<00:03, 21.54it/s] Loading 0: 77%|███████▋ | 223/291 [00:05<00:02, 28.56it/s] Loading 0: 80%|███████▉ | 232/291 [00:05<00:01, 36.60it/s] Loading 0: 83%|████████▎ | 241/291 [00:05<00:01, 42.62it/s] Loading 0: 86%|████████▌ | 250/291 [00:05<00:00, 47.04it/s] Loading 0: 89%|████████▉ | 259/291 [00:06<00:00, 54.63it/s] Loading 0: 92%|█████████▏| 268/291 [00:06<00:00, 58.64it/s] Loading 0: 95%|█████████▌| 277/291 [00:06<00:00, 62.32it/s] Loading 0: 98%|█████████▊| 286/291 [00:06<00:00, 63.69it/s]
Job sanchuanhehe-adjusted-co-1115-v1-mkmlizer completed after 73.19s with status: succeeded
Stopping job with name sanchuanhehe-adjusted-co-1115-v1-mkmlizer
Pipeline stage MKMLizer completed in 73.63s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service sanchuanhehe-adjusted-co-1115-v1
Waiting for inference service sanchuanhehe-adjusted-co-1115-v1 to be ready
Failed to get response for submission blend_hokok_2024-09-09: ('http://neversleep-noromaid-v0-8068-v150-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Failed to get response for submission blend_hokok_2024-09-09: ('http://neversleep-noromaid-v0-8068-v150-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Inference service sanchuanhehe-adjusted-co-1115-v1 ready after 191.16035509109497s
Pipeline stage MKMLDeployer completed in 191.51s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.0481452941894531s
Received healthy response to inference request in 2.7543606758117676s
Received healthy response to inference request in 1.2429835796356201s
Received healthy response to inference request in 0.9365417957305908s
Received healthy response to inference request in 0.8103995323181152s
5 requests
0 failed requests
5th percentile: 0.8356279850006103
10th percentile: 0.8608564376831055
20th percentile: 0.9113133430480957
30th percentile: 0.9588624954223632
40th percentile: 1.0035038948059083
50th percentile: 1.0481452941894531
60th percentile: 1.12608060836792
70th percentile: 1.2040159225463867
80th percentile: 1.5452589988708498
90th percentile: 2.1498098373413086
95th percentile: 2.4520852565765376
99th percentile: 2.6939055919647217
mean time: 1.3584861755371094
Pipeline stage StressChecker completed in 7.53s
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 4.56s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_1115_v1 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 sanchuanhehe-adjusted-co-1115-v1-profiler
Waiting for inference service sanchuanhehe-adjusted-co-1115-v1-profiler to be ready
Inference service sanchuanhehe-adjusted-co-1115-v1-profiler ready after 190.43515920639038s
Pipeline stage MKMLProfilerDeployer completed in 191.82s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/sanchuanhehe-adjustefa254ac9b05941f336052678017d3210-deploh48nb:/code/chaiverse_profiler_1726579194 --namespace tenant-chaiml-guanaco
kubectl exec -it sanchuanhehe-adjustefa254ac9b05941f336052678017d3210-deploh48nb --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726579194 && python profiles.py profile --best_of_n 1 --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_1726579194/summary.json'
kubectl exec -it sanchuanhehe-adjustefa254ac9b05941f336052678017d3210-deploh48nb --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726579194/summary.json'
Pipeline stage MKMLProfilerRunner completed in 465.61s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service sanchuanhehe-adjusted-co-1115-v1-profiler is running
Tearing down inference service sanchuanhehe-adjusted-co-1115-v1-profiler
Service sanchuanhehe-adjusted-co-1115-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.92s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_1115_v1 status is now inactive due to auto deactivation removed underperforming models
sanchuanhehe-adjusted-co_1115_v1 status is now torndown due to DeploymentManager action