developer_uid: sanchuanhehe
submission_id: sanchuanhehe-adjusted-co_9812_v1
model_name: sanchuanhehe-adjusted-co_9812_v1
model_group: sanchuanhehe/adjusted_co
status: torndown
timestamp: 2024-09-17T13:06:36+00:00
num_battles: 9917
num_wins: 4103
celo_rating: 1113.84
family_friendly_score: 0.0
submission_type: basic
model_repo: sanchuanhehe/adjusted_config_7_le
model_architecture: MistralForCausalLM
model_num_parameters: 7241732096.0
best_of: 1
max_input_tokens: 512
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 1.125425698008883, 'latency_mean': 0.8884750926494598, 'latency_p50': 0.8817120790481567, 'latency_p90': 0.9933093786239624}, {'batch_size': 5, 'throughput': 3.658496419155078, 'latency_mean': 1.3605623733997345, 'latency_p50': 1.366193175315857, 'latency_p90': 1.5226526737213135}, {'batch_size': 10, 'throughput': 5.424537768371242, 'latency_mean': 1.8220307981967927, 'latency_p50': 1.8257170915603638, 'latency_p90': 2.062176966667175}, {'batch_size': 15, 'throughput': 6.358324479785886, 'latency_mean': 2.311862599849701, 'latency_p50': 2.300842761993408, 'latency_p90': 2.6738118171691894}, {'batch_size': 20, 'throughput': 6.903908752940759, 'latency_mean': 2.837001757621765, 'latency_p50': 2.856307864189148, 'latency_p90': 3.226957082748413}, {'batch_size': 25, 'throughput': 7.258210142625606, 'latency_mean': 3.3793046832084657, 'latency_p50': 3.3644087314605713, 'latency_p90': 3.8951973915100098}, {'batch_size': 30, 'throughput': 7.55046405615842, 'latency_mean': 3.890068999528885, 'latency_p50': 3.9011576175689697, 'latency_p90': 4.480640530586243}, {'batch_size': 35, 'throughput': 7.61369212571393, 'latency_mean': 4.472895160913468, 'latency_p50': 4.393034815788269, 'latency_p90': 5.526088500022888}, {'batch_size': 40, 'throughput': 7.715381764103812, 'latency_mean': 5.018949952125549, 'latency_p50': 4.9605937004089355, 'latency_p90': 6.175005793571472}, {'batch_size': 45, 'throughput': 7.688813133110179, 'latency_mean': 5.618408483266831, 'latency_p50': 5.5411553382873535, 'latency_p90': 6.633937358856201}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: sanchuanhehe-adjusted-co_9812_v1
is_internal_developer: False
language_model: sanchuanhehe/adjusted_config_7_le
model_size: 7B
ranking_group: single
throughput_3p7s: 7.61
us_pacific_date: 2024-09-17
win_ratio: 0.4137339921347182
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-9812-v1-mkmlizer
Waiting for job on sanchuanhehe-adjusted-co-9812-v1-mkmlizer to finish
sanchuanhehe-adjusted-co-9812-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sanchuanhehe-adjusted-co-9812-v1-mkmlizer: ║     _____            __           __                                ║
sanchuanhehe-adjusted-co-9812-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sanchuanhehe-adjusted-co-9812-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sanchuanhehe-adjusted-co-9812-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sanchuanhehe-adjusted-co-9812-v1-mkmlizer: ║       /___/                                                         ║
sanchuanhehe-adjusted-co-9812-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-9812-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
sanchuanhehe-adjusted-co-9812-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sanchuanhehe-adjusted-co-9812-v1-mkmlizer: ║  https://mk1.ai                                                     ║
sanchuanhehe-adjusted-co-9812-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-9812-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
sanchuanhehe-adjusted-co-9812-v1-mkmlizer: ║  belonging to:                                                      ║
sanchuanhehe-adjusted-co-9812-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-9812-v1-mkmlizer: ║  Chai Research Corp.                                                ║
sanchuanhehe-adjusted-co-9812-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sanchuanhehe-adjusted-co-9812-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sanchuanhehe-adjusted-co-9812-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-9812-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', '')
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-9812-v1-mkmlizer: Downloaded to shared memory in 31.288s
sanchuanhehe-adjusted-co-9812-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp21rhjuvc, device:0
sanchuanhehe-adjusted-co-9812-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sanchuanhehe-adjusted-co-9812-v1-mkmlizer: quantized model in 18.094s
sanchuanhehe-adjusted-co-9812-v1-mkmlizer: Processed model sanchuanhehe/adjusted_config_7_le in 49.382s
sanchuanhehe-adjusted-co-9812-v1-mkmlizer: creating bucket guanaco-mkml-models
sanchuanhehe-adjusted-co-9812-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sanchuanhehe-adjusted-co-9812-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-9812-v1
sanchuanhehe-adjusted-co-9812-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-9812-v1/tokenizer_config.json
sanchuanhehe-adjusted-co-9812-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-9812-v1/special_tokens_map.json
sanchuanhehe-adjusted-co-9812-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-9812-v1/config.json
sanchuanhehe-adjusted-co-9812-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-9812-v1/tokenizer.model
sanchuanhehe-adjusted-co-9812-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-9812-v1/tokenizer.json
sanchuanhehe-adjusted-co-9812-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-9812-v1/flywheel_model.0.safetensors
sanchuanhehe-adjusted-co-9812-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:05, 51.56it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:04, 67.63it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:07, 37.43it/s]
Loading 0:  12%|█▏        | 34/291 [00:00<00:05, 46.16it/s]
Loading 0:  15%|█▍        | 43/291 [00:00<00:04, 55.92it/s]
Loading 0:  20%|█▉        | 58/291 [00:00<00:03, 71.76it/s]
Loading 0:  24%|██▍       | 70/291 [00:01<00:02, 75.80it/s]
Loading 0:  29%|██▉       | 85/291 [00:01<00:02, 85.24it/s]
Loading 0:  33%|███▎      | 95/291 [00:01<00:02, 88.11it/s]
Loading 0:  36%|███▌      | 105/291 [00:02<00:07, 25.53it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:05, 31.17it/s]
Loading 0:  43%|████▎     | 124/291 [00:02<00:04, 36.79it/s]
Loading 0:  46%|████▌     | 133/291 [00:02<00:03, 43.05it/s]
Loading 0:  49%|████▉     | 142/291 [00:02<00:02, 50.37it/s]
Loading 0:  52%|█████▏    | 152/291 [00:03<00:02, 59.35it/s]
Loading 0:  55%|█████▌    | 161/291 [00:03<00:02, 64.68it/s]
Loading 0:  58%|█████▊    | 170/291 [00:03<00:01, 67.00it/s]
Loading 0:  62%|██████▏   | 179/291 [00:03<00:01, 68.44it/s]
Loading 0:  64%|██████▍   | 187/291 [00:03<00:01, 70.55it/s]
Loading 0:  67%|██████▋   | 196/291 [00:03<00:01, 74.88it/s]
Loading 0:  70%|███████   | 205/291 [00:04<00:03, 22.46it/s]
Loading 0:  74%|███████▎  | 214/291 [00:04<00:02, 28.43it/s]
Loading 0:  77%|███████▋  | 223/291 [00:04<00:01, 34.95it/s]
Loading 0:  80%|███████▉  | 232/291 [00:05<00:01, 40.95it/s]
Loading 0:  83%|████████▎ | 241/291 [00:05<00:01, 47.12it/s]
Loading 0:  86%|████████▌ | 250/291 [00:05<00:00, 51.63it/s]
Loading 0:  89%|████████▉ | 259/291 [00:05<00:00, 56.70it/s]
Loading 0:  92%|█████████▏| 268/291 [00:05<00:00, 59.38it/s]
Loading 0:  95%|█████████▌| 277/291 [00:05<00:00, 63.04it/s]
Loading 0:  98%|█████████▊| 286/291 [00:05<00:00, 64.15it/s]
                                                            

Job sanchuanhehe-adjusted-co-9812-v1-mkmlizer completed after 74.03s with status: succeeded
Stopping job with name sanchuanhehe-adjusted-co-9812-v1-mkmlizer
Pipeline stage MKMLizer completed in 74.75s
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-9812-v1
Waiting for inference service sanchuanhehe-adjusted-co-9812-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
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
Inference service sanchuanhehe-adjusted-co-9812-v1 ready after 170.77383470535278s
Pipeline stage MKMLDeployer completed in 171.12s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 0.8799796104431152s
Received healthy response to inference request in 1.4355792999267578s
Received healthy response to inference request in 0.8388972282409668s
Received healthy response to inference request in 0.6857495307922363s
Received healthy response to inference request in 1.315424919128418s
5 requests
0 failed requests
5th percentile: 0.7163790702819824
10th percentile: 0.7470086097717286
20th percentile: 0.8082676887512207
30th percentile: 0.8471137046813965
40th percentile: 0.8635466575622559
50th percentile: 0.8799796104431152
60th percentile: 1.0541577339172363
70th percentile: 1.2283358573913574
80th percentile: 1.339455795288086
90th percentile: 1.387517547607422
95th percentile: 1.4115484237670899
99th percentile: 1.4307731246948243
mean time: 1.031126117706299
Pipeline stage StressChecker completed in 7.16s
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 5.21s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_9812_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 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service sanchuanhehe-adjusted-co-9812-v1-profiler
Waiting for inference service sanchuanhehe-adjusted-co-9812-v1-profiler to be ready
Inference service sanchuanhehe-adjusted-co-9812-v1-profiler ready after 190.4357750415802s
Pipeline stage MKMLProfilerDeployer completed in 190.79s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/sanchuanhehe-adjuste3e40a24c81ff2933541104d56f66b8c6-deplorvh55:/code/chaiverse_profiler_1726578892 --namespace tenant-chaiml-guanaco
kubectl exec -it sanchuanhehe-adjuste3e40a24c81ff2933541104d56f66b8c6-deplorvh55 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726578892 && 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_1726578892/summary.json'
kubectl exec -it sanchuanhehe-adjuste3e40a24c81ff2933541104d56f66b8c6-deplorvh55 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726578892/summary.json'
Pipeline stage MKMLProfilerRunner completed in 466.62s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service sanchuanhehe-adjusted-co-9812-v1-profiler is running
Tearing down inference service sanchuanhehe-adjusted-co-9812-v1-profiler
Service sanchuanhehe-adjusted-co-9812-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.04s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_9812_v1 status is now inactive due to auto deactivation removed underperforming models
sanchuanhehe-adjusted-co_9812_v1 status is now torndown due to DeploymentManager action