sanchuanhehe-adjusted-co_6176

developer_uid: sanchuanhehe

submission_id: sanchuanhehe-adjusted-co_6176_v1

model_name: sanchuanhehe-adjusted-co_6176_v1

model_group: sanchuanhehe/adjusted_co

status: torndown

timestamp: 2024-09-17T13:13:09+00:00

num_battles: 10759

num_wins: 4486

celo_rating: 1115.04

family_friendly_score: 0.0

submission_type: basic

model_repo: sanchuanhehe/adjusted_config_25_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': 1.1032426162885898, 'latency_mean': 0.9063552510738373, 'latency_p50': 0.9057565927505493, 'latency_p90': 1.0079198122024535}, {'batch_size': 5, 'throughput': 3.594968440924709, 'latency_mean': 1.376555733680725, 'latency_p50': 1.3844873905181885, 'latency_p90': 1.5397212743759154}, {'batch_size': 10, 'throughput': 5.314571813309634, 'latency_mean': 1.8610838675498962, 'latency_p50': 1.8570384979248047, 'latency_p90': 2.1328071117401124}, {'batch_size': 15, 'throughput': 6.217873452394113, 'latency_mean': 2.37669886469841, 'latency_p50': 2.375607967376709, 'latency_p90': 2.7364553213119507}, {'batch_size': 20, 'throughput': 6.761864038894312, 'latency_mean': 2.9052832496166228, 'latency_p50': 2.8780823945999146, 'latency_p90': 3.3425021886825563}, {'batch_size': 25, 'throughput': 7.081449832062437, 'latency_mean': 3.4540046668052673, 'latency_p50': 3.4556907415390015, 'latency_p90': 3.978947949409485}, {'batch_size': 30, 'throughput': 7.299004886576699, 'latency_mean': 4.008135104179383, 'latency_p50': 3.969923973083496, 'latency_p90': 4.674243235588074}, {'batch_size': 35, 'throughput': 7.36481840682043, 'latency_mean': 4.634170551300048, 'latency_p50': 4.576959848403931, 'latency_p90': 5.315749406814575}, {'batch_size': 40, 'throughput': 7.478151971279131, 'latency_mean': 5.177382521629333, 'latency_p50': 5.187700986862183, 'latency_p90': 5.938049983978272}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: sanchuanhehe-adjusted-co_6176_v1

is_internal_developer: False

language_model: sanchuanhehe/adjusted_config_25_l

model_size: 7B

ranking_group: single

throughput_3p7s: 7.36

us_pacific_date: 2024-09-17

win_ratio: 0.41695324844316384

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-6176-v1-mkmlizer
Waiting for job on sanchuanhehe-adjusted-co-6176-v1-mkmlizer to finish
sanchuanhehe-adjusted-co-6176-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sanchuanhehe-adjusted-co-6176-v1-mkmlizer: ║     _____            __           __                                ║
sanchuanhehe-adjusted-co-6176-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sanchuanhehe-adjusted-co-6176-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sanchuanhehe-adjusted-co-6176-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sanchuanhehe-adjusted-co-6176-v1-mkmlizer: ║       /___/                                                         ║
sanchuanhehe-adjusted-co-6176-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-6176-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
sanchuanhehe-adjusted-co-6176-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sanchuanhehe-adjusted-co-6176-v1-mkmlizer: ║  https://mk1.ai                                                     ║
sanchuanhehe-adjusted-co-6176-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-6176-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
sanchuanhehe-adjusted-co-6176-v1-mkmlizer: ║  belonging to:                                                      ║
sanchuanhehe-adjusted-co-6176-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-6176-v1-mkmlizer: ║  Chai Research Corp.                                                ║
sanchuanhehe-adjusted-co-6176-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sanchuanhehe-adjusted-co-6176-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sanchuanhehe-adjusted-co-6176-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-6176-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Inference service sanchuanhehe-adjusted-co-5866-v1 ready after 182.22999501228333s
Pipeline stage MKMLDeployer completed in 184.66s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1966772079467773s
Received healthy response to inference request in 0.46074533462524414s
Received healthy response to inference request in 0.9499931335449219s
Received healthy response to inference request in 1.0784142017364502s
Received healthy response to inference request in 1.2490811347961426s
5 requests
0 failed requests
5th percentile: 0.5585948944091796
10th percentile: 0.6564444541931153
20th percentile: 0.8521435737609864
30th percentile: 0.9756773471832275
40th percentile: 1.027045774459839
50th percentile: 1.0784142017364502
60th percentile: 1.146680974960327
70th percentile: 1.2149477481842041
80th percentile: 1.4386003494262698
90th percentile: 1.8176387786865236
95th percentile: 2.00715799331665
99th percentile: 2.158773365020752
mean time: 1.1869822025299073
Pipeline stage StressChecker completed in 8.69s
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 4.79s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_5866_v1 status is now deployed due to DeploymentManager action
sanchuanhehe-adjusted-co-6176-v1-mkmlizer: Downloaded to shared memory in 32.840s
sanchuanhehe-adjusted-co-6176-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpwln4l1gn, device:0
sanchuanhehe-adjusted-co-6176-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sanchuanhehe-adjusted-co-6176-v1-mkmlizer: quantized model in 18.131s
sanchuanhehe-adjusted-co-6176-v1-mkmlizer: Processed model sanchuanhehe/adjusted_config_25_l in 50.971s
sanchuanhehe-adjusted-co-6176-v1-mkmlizer: creating bucket guanaco-mkml-models
sanchuanhehe-adjusted-co-6176-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sanchuanhehe-adjusted-co-6176-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-6176-v1
sanchuanhehe-adjusted-co-6176-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-6176-v1/config.json
sanchuanhehe-adjusted-co-6176-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-6176-v1/tokenizer_config.json
sanchuanhehe-adjusted-co-6176-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-6176-v1/special_tokens_map.json
sanchuanhehe-adjusted-co-6176-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-6176-v1/tokenizer.model
sanchuanhehe-adjusted-co-6176-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-6176-v1/tokenizer.json
sanchuanhehe-adjusted-co-6176-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:05, 49.73it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:04, 58.93it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:04, 66.59it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:04, 64.96it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:03, 67.31it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:03, 70.95it/s]
Loading 0:  20%|█▉        | 58/291 [00:00<00:03, 72.66it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:03, 73.80it/s]
Loading 0:  26%|██▌       | 76/291 [00:01<00:02, 73.19it/s]
Loading 0:  29%|██▉       | 85/291 [00:01<00:02, 71.69it/s]
Loading 0:  32%|███▏      | 94/291 [00:01<00:02, 72.02it/s]
Loading 0:  35%|███▌      | 102/291 [00:02<00:09, 20.58it/s]
Loading 0:  37%|███▋      | 108/291 [00:02<00:07, 23.02it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:06, 26.99it/s]
Loading 0:  43%|████▎     | 124/291 [00:02<00:05, 32.23it/s]
Loading 0:  45%|████▍     | 130/291 [00:03<00:04, 34.73it/s]
Loading 0:  48%|████▊     | 139/291 [00:03<00:03, 42.89it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:02, 50.97it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:02, 58.71it/s]
Loading 0:  57%|█████▋    | 166/291 [00:03<00:01, 65.08it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:01, 69.61it/s]
Loading 0:  63%|██████▎   | 184/291 [00:03<00:01, 74.10it/s]
Loading 0:  66%|██████▋   | 193/291 [00:03<00:01, 77.00it/s]
Loading 0:  69%|██████▉   | 202/291 [00:03<00:01, 75.88it/s]
Loading 0:  72%|███████▏  | 210/291 [00:04<00:03, 21.60it/s]
Loading 0:  74%|███████▍  | 216/291 [00:05<00:03, 24.34it/s]
Loading 0:  77%|███████▋  | 223/291 [00:05<00:02, 29.36it/s]
Loading 0:  80%|███████▉  | 232/291 [00:05<00:01, 37.95it/s]
Loading 0:  83%|████████▎ | 241/291 [00:05<00:01, 43.43it/s]
Loading 0:  86%|████████▌ | 250/291 [00:05<00:00, 49.19it/s]
Loading 0:  89%|████████▉ | 259/291 [00:05<00:00, 55.88it/s]
Loading 0:  92%|█████████▏| 268/291 [00:05<00:00, 59.31it/s]
Loading 0:  95%|█████████▌| 277/291 [00:05<00:00, 61.11it/s]
Loading 0:  98%|█████████▊| 286/291 [00:06<00:00, 66.65it/s]
                                                            
Job sanchuanhehe-adjusted-co-6176-v1-mkmlizer completed after 74.67s with status: succeeded
Stopping job with name sanchuanhehe-adjusted-co-6176-v1-mkmlizer
Pipeline stage MKMLizer completed in 75.19s
run pipeline stage %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service sanchuanhehe-adjusted-co-6176-v1
Waiting for inference service sanchuanhehe-adjusted-co-6176-v1 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
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-6176-v1 ready after 191.7164056301117s
Pipeline stage MKMLDeployer completed in 192.03s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.125121831893921s
Received healthy response to inference request in 1.6362168788909912s
Received healthy response to inference request in 1.4620985984802246s
Received healthy response to inference request in 0.8596436977386475s
Received healthy response to inference request in 1.1339161396026611s
5 requests
0 failed requests
5th percentile: 0.9144981861114502
10th percentile: 0.9693526744842529
20th percentile: 1.0790616512298583
30th percentile: 1.199552631378174
40th percentile: 1.3308256149291993
50th percentile: 1.4620985984802246
60th percentile: 1.5317459106445312
70th percentile: 1.601393222808838
80th percentile: 1.7339978694915772
90th percentile: 1.9295598506927492
95th percentile: 2.0273408412933347
99th percentile: 2.1055656337738036
mean time: 1.443399429321289
Pipeline stage StressChecker completed in 7.96s
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 4.34s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_6176_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 0.18s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service sanchuanhehe-adjusted-co-6176-v1-profiler
Waiting for inference service sanchuanhehe-adjusted-co-6176-v1-profiler to be ready
Inference service sanchuanhehe-adjusted-co-6176-v1-profiler ready after 190.43580222129822s
Pipeline stage MKMLProfilerDeployer completed in 190.85s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/sanchuanhehe-adjuste32a65b3f6a14bca7a697b50bf4592674-deplopn5j2:/code/chaiverse_profiler_1726579298 --namespace tenant-chaiml-guanaco
kubectl exec -it sanchuanhehe-adjuste32a65b3f6a14bca7a697b50bf4592674-deplopn5j2 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726579298 && 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_1726579298/summary.json'
kubectl exec -it sanchuanhehe-adjuste32a65b3f6a14bca7a697b50bf4592674-deplopn5j2 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726579298/summary.json'
Pipeline stage MKMLProfilerRunner completed in 450.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service sanchuanhehe-adjusted-co-6176-v1-profiler is running
Tearing down inference service sanchuanhehe-adjusted-co-6176-v1-profiler
Service sanchuanhehe-adjusted-co-6176-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.08s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_6176_v1 status is now inactive due to auto deactivation removed underperforming models
sanchuanhehe-adjusted-co_6176_v1 status is now torndown due to DeploymentManager action