sanchuanhehe-adjusted-co_7252

developer_uid: sanchuanhehe

submission_id: sanchuanhehe-adjusted-co_7252_v1

model_name: sanchuanhehe-adjusted-co_7252_v1

model_group: sanchuanhehe/adjusted_co

status: torndown

timestamp: 2024-09-17T13:10:49+00:00

num_battles: 11198

num_wins: 4727

celo_rating: 1118.57

family_friendly_score: 0.0

submission_type: basic

model_repo: sanchuanhehe/adjusted_config_17_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': 1.1193299695004157, 'latency_mean': 0.8932953691482544, 'latency_p50': 0.8950504064559937, 'latency_p90': 1.001592993736267}, {'batch_size': 5, 'throughput': 3.6050284938196206, 'latency_mean': 1.37274778008461, 'latency_p50': 1.3695759773254395, 'latency_p90': 1.514889645576477}, {'batch_size': 10, 'throughput': 5.320882541797996, 'latency_mean': 1.8542985916137695, 'latency_p50': 1.8480266332626343, 'latency_p90': 2.0958364725112917}, {'batch_size': 15, 'throughput': 6.207182342293111, 'latency_mean': 2.3731266546249388, 'latency_p50': 2.3697690963745117, 'latency_p90': 2.7383800268173215}, {'batch_size': 20, 'throughput': 6.872578038333491, 'latency_mean': 2.868916325569153, 'latency_p50': 2.8419324159622192, 'latency_p90': 3.3227478742599486}, {'batch_size': 25, 'throughput': 7.147141453293139, 'latency_mean': 3.4217325818538664, 'latency_p50': 3.375182628631592, 'latency_p90': 3.9866101026535032}, {'batch_size': 30, 'throughput': 7.486960998518273, 'latency_mean': 3.9263894712924956, 'latency_p50': 3.8917112350463867, 'latency_p90': 4.580337929725647}, {'batch_size': 35, 'throughput': 7.608821711325647, 'latency_mean': 4.47616929769516, 'latency_p50': 4.4044705629348755, 'latency_p90': 5.464025402069091}, {'batch_size': 40, 'throughput': 7.485476101248736, 'latency_mean': 5.159450392723084, 'latency_p50': 5.102910995483398, 'latency_p90': 5.97590491771698}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: sanchuanhehe-adjusted-co_7252_v1

is_internal_developer: False

language_model: sanchuanhehe/adjusted_config_17_l

model_size: 7B

ranking_group: single

throughput_3p7s: 7.5

us_pacific_date: 2024-09-17

win_ratio: 0.4221289515984997

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-7252-v1-mkmlizer
Waiting for job on sanchuanhehe-adjusted-co-7252-v1-mkmlizer to finish
sanchuanhehe-adjusted-co-7252-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sanchuanhehe-adjusted-co-7252-v1-mkmlizer: ║     _____            __           __                                ║
sanchuanhehe-adjusted-co-7252-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sanchuanhehe-adjusted-co-7252-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sanchuanhehe-adjusted-co-7252-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sanchuanhehe-adjusted-co-7252-v1-mkmlizer: ║       /___/                                                         ║
sanchuanhehe-adjusted-co-7252-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-7252-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
sanchuanhehe-adjusted-co-7252-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sanchuanhehe-adjusted-co-7252-v1-mkmlizer: ║  https://mk1.ai                                                     ║
sanchuanhehe-adjusted-co-7252-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-7252-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
sanchuanhehe-adjusted-co-7252-v1-mkmlizer: ║  belonging to:                                                      ║
sanchuanhehe-adjusted-co-7252-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-7252-v1-mkmlizer: ║  Chai Research Corp.                                                ║
sanchuanhehe-adjusted-co-7252-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sanchuanhehe-adjusted-co-7252-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sanchuanhehe-adjusted-co-7252-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-7252-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-7252-v1-mkmlizer: Downloaded to shared memory in 31.542s
sanchuanhehe-adjusted-co-7252-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpo709x2ul, device:0
sanchuanhehe-adjusted-co-7252-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
sanchuanhehe-adjusted-co-7252-v1-mkmlizer: quantized model in 18.458s
sanchuanhehe-adjusted-co-7252-v1-mkmlizer: Processed model sanchuanhehe/adjusted_config_17_l in 50.001s
sanchuanhehe-adjusted-co-7252-v1-mkmlizer: creating bucket guanaco-mkml-models
sanchuanhehe-adjusted-co-7252-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sanchuanhehe-adjusted-co-7252-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-7252-v1
sanchuanhehe-adjusted-co-7252-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-7252-v1/config.json
sanchuanhehe-adjusted-co-7252-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-7252-v1/tokenizer_config.json
sanchuanhehe-adjusted-co-7252-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-7252-v1/special_tokens_map.json
sanchuanhehe-adjusted-co-7252-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-7252-v1/tokenizer.model
sanchuanhehe-adjusted-co-7252-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-7252-v1/tokenizer.json
sanchuanhehe-adjusted-co-7252-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-7252-v1/flywheel_model.0.safetensors
sanchuanhehe-adjusted-co-7252-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:06, 42.45it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:05, 51.76it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:04, 60.93it/s]
Loading 0:  12%|█▏        | 34/291 [00:00<00:03, 64.52it/s]
Loading 0:  15%|█▍        | 43/291 [00:00<00:03, 69.56it/s]
Loading 0:  18%|█▊        | 52/291 [00:00<00:03, 68.57it/s]
Loading 0:  21%|██        | 61/291 [00:00<00:03, 71.05it/s]
Loading 0:  24%|██▍       | 70/291 [00:01<00:03, 69.37it/s]
Loading 0:  27%|██▋       | 79/291 [00:01<00:03, 68.05it/s]
Loading 0:  30%|███       | 88/291 [00:01<00:03, 65.01it/s]
Loading 0:  33%|███▎      | 97/291 [00:01<00:02, 64.76it/s]
Loading 0:  36%|███▌      | 104/291 [00:02<00:09, 18.76it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:07, 23.49it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:05, 30.38it/s]
Loading 0:  45%|████▍     | 130/291 [00:03<00:04, 35.54it/s]
Loading 0:  48%|████▊     | 139/291 [00:03<00:03, 41.22it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:03, 46.80it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:02, 51.89it/s]
Loading 0:  57%|█████▋    | 166/291 [00:03<00:02, 56.59it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:01, 58.46it/s]
Loading 0:  63%|██████▎   | 184/291 [00:03<00:01, 59.52it/s]
Loading 0:  66%|██████▋   | 193/291 [00:03<00:01, 62.14it/s]
Loading 0:  69%|██████▉   | 202/291 [00:04<00:01, 61.96it/s]
Loading 0:  72%|███████▏  | 209/291 [00:05<00:04, 20.04it/s]
Loading 0:  74%|███████▎  | 214/291 [00:05<00:03, 22.27it/s]
Loading 0:  77%|███████▋  | 223/291 [00:05<00:02, 29.52it/s]
Loading 0:  80%|███████▉  | 232/291 [00:05<00:01, 36.37it/s]
Loading 0:  83%|████████▎ | 241/291 [00:05<00:01, 43.00it/s]
Loading 0:  86%|████████▌ | 250/291 [00:05<00:00, 49.81it/s]
Loading 0:  89%|████████▉ | 259/291 [00:05<00:00, 56.81it/s]
Loading 0:  92%|█████████▏| 268/291 [00:06<00:00, 61.24it/s]
Loading 0:  95%|█████████▌| 277/291 [00:06<00:00, 64.07it/s]
Loading 0:  98%|█████████▊| 286/291 [00:06<00:00, 66.93it/s]
                                                            
Job sanchuanhehe-adjusted-co-7252-v1-mkmlizer completed after 74.96s with status: succeeded
Stopping job with name sanchuanhehe-adjusted-co-7252-v1-mkmlizer
Pipeline stage MKMLizer completed in 77.40s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 2.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service sanchuanhehe-adjusted-co-7252-v1
Waiting for inference service sanchuanhehe-adjusted-co-7252-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', '')
Inference service sanchuanhehe-adjusted-co-7252-v1 ready after 181.01500844955444s
Pipeline stage MKMLDeployer completed in 181.67s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.633134126663208s
Received healthy response to inference request in 0.946282148361206s
Received healthy response to inference request in 1.5899412631988525s
Received healthy response to inference request in 0.7974460124969482s
Received healthy response to inference request in 0.6358218193054199s
5 requests
0 failed requests
5th percentile: 0.6681466579437256
10th percentile: 0.7004714965820312
20th percentile: 0.7651211738586425
30th percentile: 0.8272132396697998
40th percentile: 0.8867476940155029
50th percentile: 0.946282148361206
60th percentile: 1.2037457942962646
70th percentile: 1.4612094402313232
80th percentile: 1.5985798358917236
90th percentile: 1.615856981277466
95th percentile: 1.624495553970337
99th percentile: 1.6314064121246339
mean time: 1.120525074005127
Pipeline stage StressChecker completed in 7.57s
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 5.04s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_7252_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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service sanchuanhehe-adjusted-co-7252-v1-profiler
Waiting for inference service sanchuanhehe-adjusted-co-7252-v1-profiler to be ready
Inference service sanchuanhehe-adjusted-co-7252-v1-profiler ready after 200.4530165195465s
Pipeline stage MKMLProfilerDeployer completed in 200.81s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/sanchuanhehe-adjuste3d78011b26171bf8d097134906642806-deploh647h:/code/chaiverse_profiler_1726579160 --namespace tenant-chaiml-guanaco
kubectl exec -it sanchuanhehe-adjuste3d78011b26171bf8d097134906642806-deploh647h --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726579160 && 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_1726579160/summary.json'
kubectl exec -it sanchuanhehe-adjuste3d78011b26171bf8d097134906642806-deploh647h --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726579160/summary.json'
Pipeline stage MKMLProfilerRunner completed in 447.73s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service sanchuanhehe-adjusted-co-7252-v1-profiler is running
Tearing down inference service sanchuanhehe-adjusted-co-7252-v1-profiler
Service sanchuanhehe-adjusted-co-7252-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.24s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_7252_v1 status is now inactive due to auto deactivation removed underperforming models
sanchuanhehe-adjusted-co_7252_v1 status is now torndown due to DeploymentManager action