sanchuanhehe-adjusted-co_1168

developer_uid: sanchuanhehe

submission_id: sanchuanhehe-adjusted-co_1168_v1

model_name: sanchuanhehe-adjusted-co_1168_v1

model_group: sanchuanhehe/adjusted_co

status: torndown

timestamp: 2024-09-17T13:15:07+00:00

num_battles: 10701

num_wins: 4459

celo_rating: 1116.3

family_friendly_score: 0.0

submission_type: basic

model_repo: sanchuanhehe/adjusted_config_33_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': 1.1091032057005317, 'latency_mean': 0.9015660500526428, 'latency_p50': 0.9093227386474609, 'latency_p90': 0.9989219188690186}, {'batch_size': 5, 'throughput': 3.6527824372876037, 'latency_mean': 1.3613874316215515, 'latency_p50': 1.3670740127563477, 'latency_p90': 1.5174609184265135}, {'batch_size': 10, 'throughput': 5.305216996012882, 'latency_mean': 1.8587567174434663, 'latency_p50': 1.8597462177276611, 'latency_p90': 2.0825695991516113}, {'batch_size': 15, 'throughput': 6.290783310813617, 'latency_mean': 2.340533797740936, 'latency_p50': 2.3421711921691895, 'latency_p90': 2.674082398414612}, {'batch_size': 20, 'throughput': 6.809832558857615, 'latency_mean': 2.883816946744919, 'latency_p50': 2.89305579662323, 'latency_p90': 3.3825750589370727}, {'batch_size': 25, 'throughput': 7.140375836591489, 'latency_mean': 3.421644368171692, 'latency_p50': 3.415268659591675, 'latency_p90': 4.048069405555725}, {'batch_size': 30, 'throughput': 7.494271135209643, 'latency_mean': 3.9121166014671327, 'latency_p50': 3.886116862297058, 'latency_p90': 4.670693898200988}, {'batch_size': 35, 'throughput': 7.607284776691953, 'latency_mean': 4.488889846801758, 'latency_p50': 4.453545928001404, 'latency_p90': 5.452131104469299}, {'batch_size': 40, 'throughput': 7.607502231027632, 'latency_mean': 5.080963665246964, 'latency_p50': 5.087428689002991, 'latency_p90': 5.885416388511657}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: sanchuanhehe-adjusted-co_1168_v1

is_internal_developer: False

language_model: sanchuanhehe/adjusted_config_33_l

model_size: 7B

ranking_group: single

throughput_3p7s: 7.52

us_pacific_date: 2024-09-17

win_ratio: 0.4166900289692552

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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Starting job with name sanchuanhehe-adjusted-co-1168-v1-mkmlizer
Waiting for job on sanchuanhehe-adjusted-co-1168-v1-mkmlizer to finish
sanchuanhehe-adjusted-co-1168-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sanchuanhehe-adjusted-co-1168-v1-mkmlizer: ║     _____            __           __                                ║
sanchuanhehe-adjusted-co-1168-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sanchuanhehe-adjusted-co-1168-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sanchuanhehe-adjusted-co-1168-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sanchuanhehe-adjusted-co-1168-v1-mkmlizer: ║       /___/                                                         ║
sanchuanhehe-adjusted-co-1168-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-1168-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
sanchuanhehe-adjusted-co-1168-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sanchuanhehe-adjusted-co-1168-v1-mkmlizer: ║  https://mk1.ai                                                     ║
sanchuanhehe-adjusted-co-1168-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-1168-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
sanchuanhehe-adjusted-co-1168-v1-mkmlizer: ║  belonging to:                                                      ║
sanchuanhehe-adjusted-co-1168-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-1168-v1-mkmlizer: ║  Chai Research Corp.                                                ║
sanchuanhehe-adjusted-co-1168-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sanchuanhehe-adjusted-co-1168-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sanchuanhehe-adjusted-co-1168-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-1168-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sanchuanhehe-adjusted-co-1168-v1-mkmlizer: Downloaded to shared memory in 30.214s
sanchuanhehe-adjusted-co-1168-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmppoohy5wk, device:0
sanchuanhehe-adjusted-co-1168-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
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-1168-v1-mkmlizer: quantized model in 17.510s
sanchuanhehe-adjusted-co-1168-v1-mkmlizer: Processed model sanchuanhehe/adjusted_config_33_l in 47.724s
sanchuanhehe-adjusted-co-1168-v1-mkmlizer: creating bucket guanaco-mkml-models
sanchuanhehe-adjusted-co-1168-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sanchuanhehe-adjusted-co-1168-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-1168-v1
sanchuanhehe-adjusted-co-1168-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-1168-v1/special_tokens_map.json
sanchuanhehe-adjusted-co-1168-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-1168-v1/config.json
sanchuanhehe-adjusted-co-1168-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-1168-v1/tokenizer_config.json
sanchuanhehe-adjusted-co-1168-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-1168-v1/tokenizer.model
sanchuanhehe-adjusted-co-1168-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-1168-v1/tokenizer.json
sanchuanhehe-adjusted-co-1168-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-1168-v1/flywheel_model.0.safetensors
sanchuanhehe-adjusted-co-1168-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:06, 45.41it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:04, 61.17it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:03, 69.57it/s]
Loading 0:  11%|█▏        | 33/291 [00:00<00:03, 65.11it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:03, 64.28it/s]
Loading 0:  18%|█▊        | 52/291 [00:00<00:03, 72.70it/s]
Loading 0:  21%|██▏       | 62/291 [00:00<00:02, 80.22it/s]
Loading 0:  26%|██▌       | 76/291 [00:01<00:02, 89.23it/s]
Loading 0:  30%|███       | 88/291 [00:01<00:02, 89.08it/s]
Loading 0:  34%|███▎      | 98/291 [00:02<00:07, 25.07it/s]
Loading 0:  36%|███▋      | 106/291 [00:02<00:06, 29.20it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:04, 35.98it/s]
Loading 0:  43%|████▎     | 125/291 [00:02<00:03, 44.60it/s]
Loading 0:  46%|████▌     | 134/291 [00:02<00:03, 51.68it/s]
Loading 0:  49%|████▉     | 143/291 [00:02<00:02, 58.86it/s]
Loading 0:  52%|█████▏    | 152/291 [00:02<00:02, 64.67it/s]
Loading 0:  57%|█████▋    | 166/291 [00:03<00:01, 74.69it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:01, 75.91it/s]
Loading 0:  63%|██████▎   | 184/291 [00:03<00:01, 75.58it/s]
Loading 0:  66%|██████▋   | 193/291 [00:03<00:01, 74.28it/s]
Loading 0:  69%|██████▉   | 202/291 [00:03<00:01, 77.34it/s]
Loading 0:  73%|███████▎  | 211/291 [00:04<00:03, 22.97it/s]
Loading 0:  76%|███████▌  | 220/291 [00:04<00:02, 28.95it/s]
Loading 0:  79%|███████▉  | 231/291 [00:04<00:01, 38.56it/s]
Loading 0:  82%|████████▏ | 239/291 [00:04<00:01, 43.82it/s]
Loading 0:  85%|████████▍ | 247/291 [00:05<00:00, 47.99it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 55.03it/s]
Loading 0:  91%|█████████▏| 266/291 [00:05<00:00, 64.22it/s]
Loading 0:  95%|█████████▍| 275/291 [00:05<00:00, 69.49it/s]
Loading 0:  98%|█████████▊| 284/291 [00:05<00:00, 70.29it/s]
                                                            
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', '')
Job sanchuanhehe-adjusted-co-1168-v1-mkmlizer completed after 73.87s with status: succeeded
Stopping job with name sanchuanhehe-adjusted-co-1168-v1-mkmlizer
Pipeline stage MKMLizer completed in 76.08s
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-1168-v1
Waiting for inference service sanchuanhehe-adjusted-co-1168-v1 to be ready
Inference service sanchuanhehe-adjusted-co-1168-v1 ready after 181.00745153427124s
Pipeline stage MKMLDeployer completed in 182.06s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.611964464187622s
Received healthy response to inference request in 0.7233660221099854s
Received healthy response to inference request in 1.1780281066894531s
Received healthy response to inference request in 0.8406455516815186s
Received healthy response to inference request in 0.9865798950195312s
5 requests
0 failed requests
5th percentile: 0.746821928024292
10th percentile: 0.7702778339385986
20th percentile: 0.8171896457672119
30th percentile: 0.8698324203491211
40th percentile: 0.9282061576843261
50th percentile: 0.9865798950195312
60th percentile: 1.0631591796875
70th percentile: 1.1397384643554687
80th percentile: 1.264815378189087
90th percentile: 1.4383899211883546
95th percentile: 1.5251771926879882
99th percentile: 1.5946070098876952
mean time: 1.068116807937622
Pipeline stage StressChecker completed in 6.09s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Pipeline stage TriggerMKMLProfilingPipeline completed in 4.66s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_1168_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-1168-v1-profiler
Waiting for inference service sanchuanhehe-adjusted-co-1168-v1-profiler to be ready
Inference service sanchuanhehe-adjusted-co-1168-v1-profiler ready after 190.46340489387512s
Pipeline stage MKMLProfilerDeployer completed in 190.82s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/sanchuanhehe-adjuste25e262f6ef6b0c6dcf71e40e71be80a1-deplo8nmbf:/code/chaiverse_profiler_1726579402 --namespace tenant-chaiml-guanaco
kubectl exec -it sanchuanhehe-adjuste25e262f6ef6b0c6dcf71e40e71be80a1-deplo8nmbf --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726579402 && 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_1726579402/summary.json'
kubectl exec -it sanchuanhehe-adjuste25e262f6ef6b0c6dcf71e40e71be80a1-deplo8nmbf --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726579402/summary.json'
Pipeline stage MKMLProfilerRunner completed in 446.50s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service sanchuanhehe-adjusted-co-1168-v1-profiler is running
Tearing down inference service sanchuanhehe-adjusted-co-1168-v1-profiler
Service sanchuanhehe-adjusted-co-1168-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.17s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_1168_v1 status is now inactive due to auto deactivation removed underperforming models
sanchuanhehe-adjusted-co_1168_v1 status is now torndown due to DeploymentManager action