sanchuanhehe-adjusted-co_1921

developer_uid: sanchuanhehe

submission_id: sanchuanhehe-adjusted-co_1921_v1

model_name: sanchuanhehe-adjusted-co_1921_v1

model_group: sanchuanhehe/adjusted_co

status: torndown

timestamp: 2024-09-17T13:13:24+00:00

num_battles: 9264

num_wins: 3910

celo_rating: 1119.04

family_friendly_score: 0.0

submission_type: basic

model_repo: sanchuanhehe/adjusted_config_26_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': 1.1041550538114888, 'latency_mean': 0.905575008392334, 'latency_p50': 0.9072216749191284, 'latency_p90': 1.0086716651916503}, {'batch_size': 5, 'throughput': 3.6120162277659493, 'latency_mean': 1.3717735922336578, 'latency_p50': 1.3775298595428467, 'latency_p90': 1.5177489042282104}, {'batch_size': 10, 'throughput': 5.359228618848959, 'latency_mean': 1.8459818494319915, 'latency_p50': 1.8277932405471802, 'latency_p90': 2.0651494741439818}, {'batch_size': 15, 'throughput': 6.154004253408692, 'latency_mean': 2.3960481548309325, 'latency_p50': 2.377368927001953, 'latency_p90': 2.7211190938949583}, {'batch_size': 20, 'throughput': 6.748151691091105, 'latency_mean': 2.909893988370895, 'latency_p50': 2.9053930044174194, 'latency_p90': 3.3190895557403564}, {'batch_size': 25, 'throughput': 7.101287881996392, 'latency_mean': 3.445411865711212, 'latency_p50': 3.417271137237549, 'latency_p90': 4.042792439460754}, {'batch_size': 30, 'throughput': 7.2939290710549445, 'latency_mean': 4.015352549552918, 'latency_p50': 4.0307856798172, 'latency_p90': 4.70568881034851}, {'batch_size': 35, 'throughput': 7.537479710571694, 'latency_mean': 4.52235158085823, 'latency_p50': 4.505217432975769, 'latency_p90': 5.386454463005066}, {'batch_size': 40, 'throughput': 7.487303478330505, 'latency_mean': 5.155372784137726, 'latency_p50': 5.085990309715271, 'latency_p90': 6.013938951492309}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: sanchuanhehe-adjusted-co_1921_v1

is_internal_developer: False

language_model: sanchuanhehe/adjusted_config_26_l

model_size: 7B

ranking_group: single

throughput_3p7s: 7.36

us_pacific_date: 2024-09-17

win_ratio: 0.4220639032815199

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-1921-v1-mkmlizer
Waiting for job on sanchuanhehe-adjusted-co-1921-v1-mkmlizer to finish
sanchuanhehe-adjusted-co-1921-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sanchuanhehe-adjusted-co-1921-v1-mkmlizer: ║     _____            __           __                                ║
sanchuanhehe-adjusted-co-1921-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sanchuanhehe-adjusted-co-1921-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sanchuanhehe-adjusted-co-1921-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sanchuanhehe-adjusted-co-1921-v1-mkmlizer: ║       /___/                                                         ║
sanchuanhehe-adjusted-co-1921-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-1921-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
sanchuanhehe-adjusted-co-1921-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sanchuanhehe-adjusted-co-1921-v1-mkmlizer: ║  https://mk1.ai                                                     ║
sanchuanhehe-adjusted-co-1921-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-1921-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
sanchuanhehe-adjusted-co-1921-v1-mkmlizer: ║  belonging to:                                                      ║
sanchuanhehe-adjusted-co-1921-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-1921-v1-mkmlizer: ║  Chai Research Corp.                                                ║
sanchuanhehe-adjusted-co-1921-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sanchuanhehe-adjusted-co-1921-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sanchuanhehe-adjusted-co-1921-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-1921-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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-1921-v1-mkmlizer: Downloaded to shared memory in 33.584s
sanchuanhehe-adjusted-co-1921-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp0jphsq6z, device:0
sanchuanhehe-adjusted-co-1921-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sanchuanhehe-adjusted-co-1921-v1-mkmlizer: quantized model in 18.240s
sanchuanhehe-adjusted-co-1921-v1-mkmlizer: Processed model sanchuanhehe/adjusted_config_26_l in 51.824s
sanchuanhehe-adjusted-co-1921-v1-mkmlizer: creating bucket guanaco-mkml-models
sanchuanhehe-adjusted-co-1921-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sanchuanhehe-adjusted-co-1921-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-1921-v1
sanchuanhehe-adjusted-co-1921-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-1921-v1/config.json
sanchuanhehe-adjusted-co-1921-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-1921-v1/special_tokens_map.json
sanchuanhehe-adjusted-co-1921-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-1921-v1/tokenizer_config.json
sanchuanhehe-adjusted-co-1921-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-1921-v1/flywheel_model.0.safetensors
sanchuanhehe-adjusted-co-1921-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:05, 50.62it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:03, 70.11it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:03, 78.44it/s]
Loading 0:  12%|█▏        | 34/291 [00:00<00:03, 82.03it/s]
Loading 0:  15%|█▍        | 43/291 [00:00<00:03, 81.03it/s]
Loading 0:  18%|█▊        | 53/291 [00:00<00:02, 86.75it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:02, 90.89it/s]
Loading 0:  26%|██▋       | 77/291 [00:00<00:02, 92.33it/s]
Loading 0:  30%|██▉       | 87/291 [00:01<00:02, 87.26it/s]
Loading 0:  33%|███▎      | 96/291 [00:01<00:02, 79.10it/s]
Loading 0:  36%|███▌      | 105/291 [00:02<00:08, 21.17it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:07, 24.83it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:05, 31.29it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:04, 37.16it/s]
Loading 0:  48%|████▊     | 139/291 [00:02<00:03, 43.87it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:02, 49.42it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:02, 54.37it/s]
Loading 0:  57%|█████▋    | 166/291 [00:03<00:02, 58.11it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:01, 60.52it/s]
Loading 0:  63%|██████▎   | 184/291 [00:03<00:01, 60.17it/s]
Loading 0:  66%|██████▋   | 193/291 [00:03<00:01, 61.38it/s]
Loading 0:  69%|██████▉   | 202/291 [00:03<00:01, 62.83it/s]
Loading 0:  72%|███████▏  | 209/291 [00:04<00:04, 20.21it/s]
Loading 0:  74%|███████▎  | 214/291 [00:05<00:03, 22.35it/s]
Loading 0:  77%|███████▋  | 223/291 [00:05<00:02, 28.20it/s]
Loading 0:  80%|███████▉  | 232/291 [00:05<00:01, 35.04it/s]
Loading 0:  83%|████████▎ | 241/291 [00:05<00:01, 40.80it/s]
Loading 0:  86%|████████▌ | 250/291 [00:05<00:00, 45.06it/s]
Loading 0:  89%|████████▉ | 259/291 [00:05<00:00, 49.66it/s]
Loading 0:  92%|█████████▏| 268/291 [00:05<00:00, 52.98it/s]
Loading 0:  95%|█████████▌| 277/291 [00:06<00:00, 55.03it/s]
Loading 0:  98%|█████████▊| 286/291 [00:06<00:00, 56.25it/s]
                                                            
Job sanchuanhehe-adjusted-co-1921-v1-mkmlizer completed after 74.6s with status: succeeded
Stopping job with name sanchuanhehe-adjusted-co-1921-v1-mkmlizer
Pipeline stage MKMLizer completed in 76.39s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service sanchuanhehe-adjusted-co-1921-v1
Waiting for inference service sanchuanhehe-adjusted-co-1921-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', '')
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_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
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-1921-v1 ready after 200.73825883865356s
Pipeline stage MKMLDeployer completed in 201.24s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.158402681350708s
Received healthy response to inference request in 0.6290733814239502s
Received healthy response to inference request in 0.7653355598449707s
Received healthy response to inference request in 1.5536859035491943s
Received healthy response to inference request in 1.1077666282653809s
5 requests
0 failed requests
5th percentile: 0.6563258171081543
10th percentile: 0.6835782527923584
20th percentile: 0.7380831241607666
30th percentile: 0.8338217735290527
40th percentile: 0.9707942008972168
50th percentile: 1.1077666282653809
60th percentile: 1.1280210494995118
70th percentile: 1.1482754707336427
80th percentile: 1.2374593257904054
90th percentile: 1.3955726146697998
95th percentile: 1.474629259109497
99th percentile: 1.5378745746612548
mean time: 1.0428528308868408
Pipeline stage StressChecker completed in 6.96s
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 8.20s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_1921_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 0.11s
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-1921-v1-profiler
Waiting for inference service sanchuanhehe-adjusted-co-1921-v1-profiler to be ready
Inference service sanchuanhehe-adjusted-co-1921-v1-profiler ready after 190.56684279441833s
Pipeline stage MKMLProfilerDeployer completed in 190.92s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/sanchuanhehe-adjustea2875266b83d89ed4b8f54b653489959-deplo8mhgd:/code/chaiverse_profiler_1726579338 --namespace tenant-chaiml-guanaco
kubectl exec -it sanchuanhehe-adjustea2875266b83d89ed4b8f54b653489959-deplo8mhgd --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726579338 && 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_1726579338/summary.json'
kubectl exec -it sanchuanhehe-adjustea2875266b83d89ed4b8f54b653489959-deplo8mhgd --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726579338/summary.json'
Pipeline stage MKMLProfilerRunner completed in 449.83s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service sanchuanhehe-adjusted-co-1921-v1-profiler is running
Tearing down inference service sanchuanhehe-adjusted-co-1921-v1-profiler
Service sanchuanhehe-adjusted-co-1921-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.00s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_1921_v1 status is now inactive due to auto deactivation removed underperforming models
sanchuanhehe-adjusted-co_1921_v1 status is now torndown due to DeploymentManager action