sanchuanhehe-adjusted-co_1356

developer_uid: sanchuanhehe

submission_id: sanchuanhehe-adjusted-co_1356_v1

model_name: sanchuanhehe-adjusted-co_1356_v1

model_group: sanchuanhehe/adjusted_co

status: torndown

timestamp: 2024-09-17T13:09:50+00:00

num_battles: 11091

num_wins: 4654

celo_rating: 1118.42

family_friendly_score: 0.0

submission_type: basic

model_repo: sanchuanhehe/adjusted_config_13_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': 1.1264945599500298, 'latency_mean': 0.8876485550403594, 'latency_p50': 0.882697582244873, 'latency_p90': 0.9946301460266114}, {'batch_size': 5, 'throughput': 3.644201236887273, 'latency_mean': 1.3589863455295563, 'latency_p50': 1.3572683334350586, 'latency_p90': 1.517303991317749}, {'batch_size': 10, 'throughput': 5.37215840670615, 'latency_mean': 1.8417933082580566, 'latency_p50': 1.8339576721191406, 'latency_p90': 2.1153131484985352}, {'batch_size': 15, 'throughput': 6.352483162293181, 'latency_mean': 2.3239684712886812, 'latency_p50': 2.3234695196151733, 'latency_p90': 2.671598434448242}, {'batch_size': 20, 'throughput': 6.906185423088828, 'latency_mean': 2.8441830599308013, 'latency_p50': 2.8329145908355713, 'latency_p90': 3.295066404342651}, {'batch_size': 25, 'throughput': 7.2712622827686895, 'latency_mean': 3.374032255411148, 'latency_p50': 3.3506845235824585, 'latency_p90': 3.865382266044616}, {'batch_size': 30, 'throughput': 7.538826094655629, 'latency_mean': 3.884072892665863, 'latency_p50': 3.8765538930892944, 'latency_p90': 4.520487117767334}, {'batch_size': 35, 'throughput': 7.72249855832746, 'latency_mean': 4.4215009617805485, 'latency_p50': 4.374314308166504, 'latency_p90': 5.42892038822174}, {'batch_size': 40, 'throughput': 7.599256026242964, 'latency_mean': 5.093833676576614, 'latency_p50': 5.086920380592346, 'latency_p90': 5.945174336433411}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: sanchuanhehe-adjusted-co_1356_v1

is_internal_developer: False

language_model: sanchuanhehe/adjusted_config_13_l

model_size: 7B

ranking_group: single

throughput_3p7s: 7.62

us_pacific_date: 2024-09-17

win_ratio: 0.41961951131548103

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-1356-v1-mkmlizer
Waiting for job on sanchuanhehe-adjusted-co-1356-v1-mkmlizer to finish
sanchuanhehe-adjusted-co-1356-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sanchuanhehe-adjusted-co-1356-v1-mkmlizer: ║     _____            __           __                                ║
sanchuanhehe-adjusted-co-1356-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sanchuanhehe-adjusted-co-1356-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sanchuanhehe-adjusted-co-1356-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sanchuanhehe-adjusted-co-1356-v1-mkmlizer: ║       /___/                                                         ║
sanchuanhehe-adjusted-co-1356-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-1356-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
sanchuanhehe-adjusted-co-1356-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sanchuanhehe-adjusted-co-1356-v1-mkmlizer: ║  https://mk1.ai                                                     ║
sanchuanhehe-adjusted-co-1356-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-1356-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
sanchuanhehe-adjusted-co-1356-v1-mkmlizer: ║  belonging to:                                                      ║
sanchuanhehe-adjusted-co-1356-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-1356-v1-mkmlizer: ║  Chai Research Corp.                                                ║
sanchuanhehe-adjusted-co-1356-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sanchuanhehe-adjusted-co-1356-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sanchuanhehe-adjusted-co-1356-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-1356-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission blend_tikob_2024-09-13: ('http://chaiml-llama-8b-pairwis-8189-v19-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:39884->127.0.0.1:8080: read: connection reset by peer\n')
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', '')
sanchuanhehe-adjusted-co-1356-v1-mkmlizer: Downloaded to shared memory in 30.287s
sanchuanhehe-adjusted-co-1356-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp02xpub0r, device:0
sanchuanhehe-adjusted-co-1356-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sanchuanhehe-adjusted-co-1356-v1-mkmlizer: quantized model in 17.647s
sanchuanhehe-adjusted-co-1356-v1-mkmlizer: Processed model sanchuanhehe/adjusted_config_13_l in 47.934s
sanchuanhehe-adjusted-co-1356-v1-mkmlizer: creating bucket guanaco-mkml-models
sanchuanhehe-adjusted-co-1356-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sanchuanhehe-adjusted-co-1356-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-1356-v1
sanchuanhehe-adjusted-co-1356-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-1356-v1/config.json
sanchuanhehe-adjusted-co-1356-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-1356-v1/tokenizer_config.json
sanchuanhehe-adjusted-co-1356-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-1356-v1/special_tokens_map.json
sanchuanhehe-adjusted-co-1356-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-1356-v1/tokenizer.model
sanchuanhehe-adjusted-co-1356-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-1356-v1/tokenizer.json
sanchuanhehe-adjusted-co-1356-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-1356-v1/flywheel_model.0.safetensors
sanchuanhehe-adjusted-co-1356-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:05, 55.15it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:03, 86.98it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:02, 91.47it/s]
Loading 0:  15%|█▍        | 43/291 [00:00<00:02, 87.60it/s]
Loading 0:  20%|█▉        | 58/291 [00:00<00:02, 96.82it/s]
Loading 0:  24%|██▍       | 70/291 [00:00<00:02, 93.17it/s]
Loading 0:  27%|██▋       | 80/291 [00:00<00:02, 93.23it/s]
Loading 0:  31%|███       | 90/291 [00:00<00:02, 92.25it/s]
Loading 0:  34%|███▍      | 100/291 [00:02<00:07, 24.85it/s]
Loading 0:  37%|███▋      | 107/291 [00:02<00:06, 28.50it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:05, 34.21it/s]
Loading 0:  43%|████▎     | 124/291 [00:02<00:04, 41.24it/s]
Loading 0:  46%|████▌     | 133/291 [00:02<00:03, 48.67it/s]
Loading 0:  49%|████▉     | 142/291 [00:02<00:02, 55.19it/s]
Loading 0:  52%|█████▏    | 151/291 [00:02<00:02, 61.39it/s]
Loading 0:  55%|█████▌    | 161/291 [00:02<00:01, 69.93it/s]
Loading 0:  58%|█████▊    | 170/291 [00:02<00:01, 74.70it/s]
Loading 0:  62%|██████▏   | 179/291 [00:03<00:01, 78.63it/s]
Loading 0:  65%|██████▍   | 188/291 [00:03<00:01, 78.95it/s]
Loading 0:  69%|██████▉   | 202/291 [00:03<00:01, 85.77it/s]
Loading 0:  73%|███████▎  | 211/291 [00:04<00:03, 24.24it/s]
Loading 0:  76%|███████▌  | 220/291 [00:04<00:02, 29.41it/s]
Loading 0:  79%|███████▉  | 230/291 [00:04<00:01, 37.37it/s]
Loading 0:  82%|████████▏ | 238/291 [00:04<00:01, 42.06it/s]
Loading 0:  85%|████████▍ | 247/291 [00:04<00:00, 48.54it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 53.46it/s]
Loading 0:  91%|█████████ | 265/291 [00:05<00:00, 60.19it/s]
Loading 0:  94%|█████████▍| 274/291 [00:05<00:00, 66.13it/s]
Loading 0:  97%|█████████▋| 283/291 [00:05<00:00, 70.77it/s]
                                                            
Job sanchuanhehe-adjusted-co-1356-v1-mkmlizer completed after 73.87s with status: succeeded
Stopping job with name sanchuanhehe-adjusted-co-1356-v1-mkmlizer
Pipeline stage MKMLizer completed in 74.49s
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 sanchuanhehe-adjusted-co-1356-v1
Waiting for inference service sanchuanhehe-adjusted-co-1356-v1 to be ready
Failed to get response for submission blend_pikis_2024-09-14: ('http://chaiml-elo-alignment-run-3-v34-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\')]"}')
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', '')
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 sanchuanhehe-adjusted-co-1356-v1 ready after 180.81112480163574s
Pipeline stage MKMLDeployer completed in 181.26s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.344855785369873s
Received healthy response to inference request in 0.8876068592071533s
Received healthy response to inference request in 0.6507372856140137s
Received healthy response to inference request in 0.721815824508667s
Received healthy response to inference request in 1.0104117393493652s
5 requests
0 failed requests
5th percentile: 0.6649529933929443
10th percentile: 0.679168701171875
20th percentile: 0.7076001167297363
30th percentile: 0.7549740314483643
40th percentile: 0.8212904453277587
50th percentile: 0.8876068592071533
60th percentile: 0.9367288112640381
70th percentile: 0.9858507633209228
80th percentile: 1.0773005485534668
90th percentile: 1.21107816696167
95th percentile: 1.2779669761657715
99th percentile: 1.3314780235290526
mean time: 0.9230854988098145
Pipeline stage StressChecker completed in 5.44s
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 6.34s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_1356_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-1356-v1-profiler
Waiting for inference service sanchuanhehe-adjusted-co-1356-v1-profiler to be ready
Inference service sanchuanhehe-adjusted-co-1356-v1-profiler ready after 190.45286297798157s
Pipeline stage MKMLProfilerDeployer completed in 190.81s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/sanchuanhehe-adjusted4c0915737b36cefc0b81d4ef0fb1dc4-deplovjsz4:/code/chaiverse_profiler_1726579094 --namespace tenant-chaiml-guanaco
kubectl exec -it sanchuanhehe-adjusted4c0915737b36cefc0b81d4ef0fb1dc4-deplovjsz4 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726579094 && 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_1726579094/summary.json'
kubectl exec -it sanchuanhehe-adjusted4c0915737b36cefc0b81d4ef0fb1dc4-deplovjsz4 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726579094/summary.json'
Pipeline stage MKMLProfilerRunner completed in 443.93s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service sanchuanhehe-adjusted-co-1356-v1-profiler is running
Tearing down inference service sanchuanhehe-adjusted-co-1356-v1-profiler
Service sanchuanhehe-adjusted-co-1356-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 4.17s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_1356_v1 status is now inactive due to auto deactivation removed underperforming models
sanchuanhehe-adjusted-co_1356_v1 status is now torndown due to DeploymentManager action