cycy233-l3-p-v3-c4

submission_id: cycy233-l3-p-v3-c4_v1

developer_uid: shiroe40

alignment_samples: 9535

alignment_score: 0.01675509857957204

best_of: 16

celo_rating: 1257.78

display_name: auto

formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}

generation_params: {'temperature': 1.0, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['<|end_header_id|>', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}

gpu_counts: {'NVIDIA RTX A5000': 1}

is_internal_developer: False

language_model: cycy233/L3-p-v3-c4

latencies: [{'batch_size': 1, 'throughput': 0.9055594361576025, 'latency_mean': 1.1041942572593688, 'latency_p50': 1.100262999534607, 'latency_p90': 1.234205150604248}, {'batch_size': 4, 'throughput': 1.7875604086845989, 'latency_mean': 2.230531493425369, 'latency_p50': 2.2323111295700073, 'latency_p90': 2.483580756187439}, {'batch_size': 5, 'throughput': 1.8739893299189225, 'latency_mean': 2.6481725859642027, 'latency_p50': 2.6516530513763428, 'latency_p90': 2.960371804237366}, {'batch_size': 8, 'throughput': 1.9648674373229529, 'latency_mean': 4.036691771745682, 'latency_p50': 4.066837430000305, 'latency_p90': 4.454218173027039}, {'batch_size': 10, 'throughput': 2.0286040099102456, 'latency_mean': 4.882907407283783, 'latency_p50': 4.84325909614563, 'latency_p90': 5.618480443954468}, {'batch_size': 12, 'throughput': 2.0290776717062466, 'latency_mean': 5.84052807688713, 'latency_p50': 5.9381022453308105, 'latency_p90': 6.663694500923157}, {'batch_size': 15, 'throughput': 1.998237466954411, 'latency_mean': 7.362335584163666, 'latency_p50': 7.475699424743652, 'latency_p90': 8.21426727771759}]

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_group: cycy233/L3-p-v3-c4

model_name: auto

model_num_parameters: 8030261248.0

model_repo: cycy233/L3-p-v3-c4

model_size: 8B

num_battles: 9535

num_wins: 4973

propriety_score: 0.7214043035107588

propriety_total_count: 883.0

ranking_group: single

status: inactive

submission_type: basic

throughput_3p7s: 1.97

timestamp: 2024-09-12T03:13:57+00:00

us_pacific_date: 2024-09-11

win_ratio: 0.5215521761929732

Download Preference Data

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 cycy233-l3-p-v3-c4-v1-mkmlizer
Waiting for job on cycy233-l3-p-v3-c4-v1-mkmlizer to finish
cycy233-l3-p-v3-c4-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-p-v3-c4-v1-mkmlizer: ║     _____            __           __                                ║
cycy233-l3-p-v3-c4-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-l3-p-v3-c4-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-l3-p-v3-c4-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-l3-p-v3-c4-v1-mkmlizer: ║       /___/                                                         ║
cycy233-l3-p-v3-c4-v1-mkmlizer: ║                                                                     ║
cycy233-l3-p-v3-c4-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
cycy233-l3-p-v3-c4-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-l3-p-v3-c4-v1-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-l3-p-v3-c4-v1-mkmlizer: ║                                                                     ║
cycy233-l3-p-v3-c4-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-l3-p-v3-c4-v1-mkmlizer: ║  belonging to:                                                      ║
cycy233-l3-p-v3-c4-v1-mkmlizer: ║                                                                     ║
cycy233-l3-p-v3-c4-v1-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-l3-p-v3-c4-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-l3-p-v3-c4-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
cycy233-l3-p-v3-c4-v1-mkmlizer: ║                                                                     ║
cycy233-l3-p-v3-c4-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-p-v3-c4-v1-mkmlizer: Downloaded to shared memory in 37.525s
cycy233-l3-p-v3-c4-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpaz4f5pnn, device:0
cycy233-l3-p-v3-c4-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-p-v3-c4-v1-mkmlizer: quantized model in 26.029s
cycy233-l3-p-v3-c4-v1-mkmlizer: Processed model cycy233/L3-p-v3-c4 in 63.554s
cycy233-l3-p-v3-c4-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-p-v3-c4-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-p-v3-c4-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-p-v3-c4-v1
cycy233-l3-p-v3-c4-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-p-v3-c4-v1/config.json
cycy233-l3-p-v3-c4-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-p-v3-c4-v1/special_tokens_map.json
cycy233-l3-p-v3-c4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-p-v3-c4-v1/tokenizer_config.json
cycy233-l3-p-v3-c4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-p-v3-c4-v1/tokenizer.json
cycy233-l3-p-v3-c4-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-p-v3-c4-v1/flywheel_model.0.safetensors
cycy233-l3-p-v3-c4-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 4/291 [00:00<00:08, 35.57it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:04, 67.73it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:03, 85.59it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:02, 84.12it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:02, 82.46it/s]
Loading 0:  20%|█▉        | 58/291 [00:00<00:02, 83.18it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:02, 83.69it/s]
Loading 0:  26%|██▌       | 76/291 [00:00<00:02, 83.18it/s]
Loading 0:  29%|██▉       | 85/291 [00:02<00:09, 21.39it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:07, 27.79it/s]
Loading 0:  36%|███▋      | 106/291 [00:02<00:05, 36.72it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:03, 49.14it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:03, 53.40it/s]
Loading 0:  48%|████▊     | 139/291 [00:02<00:02, 57.47it/s]
Loading 0:  51%|█████     | 148/291 [00:02<00:02, 62.44it/s]
Loading 0:  54%|█████▍    | 157/291 [00:02<00:02, 66.94it/s]
Loading 0:  57%|█████▋    | 166/291 [00:03<00:01, 70.37it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:01, 73.27it/s]
Loading 0:  63%|██████▎   | 184/291 [00:03<00:01, 76.95it/s]
Loading 0:  66%|██████▋   | 193/291 [00:04<00:04, 21.11it/s]
Loading 0:  69%|██████▉   | 202/291 [00:04<00:03, 27.24it/s]
Loading 0:  73%|███████▎  | 211/291 [00:04<00:02, 34.14it/s]
Loading 0:  76%|███████▌  | 220/291 [00:04<00:01, 41.83it/s]
Loading 0:  79%|███████▉  | 230/291 [00:04<00:01, 51.41it/s]
Loading 0:  82%|████████▏ | 239/291 [00:04<00:00, 58.69it/s]
Loading 0:  86%|████████▌ | 249/291 [00:05<00:00, 67.47it/s]
Loading 0:  89%|████████▉ | 259/291 [00:05<00:00, 67.25it/s]
Loading 0:  94%|█████████▍| 274/291 [00:05<00:00, 77.25it/s]
Loading 0:  97%|█████████▋| 283/291 [00:05<00:00, 80.15it/s]
                                                            
Job cycy233-l3-p-v3-c4-v1-mkmlizer completed after 83.44s with status: succeeded
Stopping job with name cycy233-l3-p-v3-c4-v1-mkmlizer
Pipeline stage MKMLizer completed in 84.15s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cycy233-l3-p-v3-c4-v1
Waiting for inference service cycy233-l3-p-v3-c4-v1 to be ready
Failed to get response for submission chaiml-llama-8b-pairwis_8189_v19: HTTPConnectionPool(host='zonemercy-virgo-edit-v1-1e5-v12-predictor.tenant-chaiml-guanaco.k2.chaiverse.com', port=80): Max retries exceeded with url: /v1/models/GPT-J-6B-lit-v2:predict (Caused by ConnectTimeoutError(<urllib3.connection.HTTPConnection object at 0x7f57ac2ee570>, 'Connection to zonemercy-virgo-edit-v1-1e5-v12-predictor.tenant-chaiml-guanaco.k2.chaiverse.com timed out. (connect timeout=None)'))
Inference service cycy233-l3-p-v3-c4-v1 ready after 170.4805941581726s
Pipeline stage MKMLDeployer completed in 170.92s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 5.891180992126465s
Received healthy response to inference request in 1.7357935905456543s
Received healthy response to inference request in 1.5438296794891357s
Received healthy response to inference request in 8.357203483581543s
Received healthy response to inference request in 1.5587024688720703s
5 requests
0 failed requests
5th percentile: 1.5468042373657227
10th percentile: 1.5497787952423097
20th percentile: 1.5557279109954834
30th percentile: 1.594120693206787
40th percentile: 1.6649571418762208
50th percentile: 1.7357935905456543
60th percentile: 3.3979485511779783
70th percentile: 5.060103511810302
80th percentile: 6.384385490417481
90th percentile: 7.370794486999512
95th percentile: 7.863998985290527
99th percentile: 8.25856258392334
mean time: 3.8173420429229736
%s, retrying in %s seconds...
Received healthy response to inference request in 1.5718414783477783s
Received healthy response to inference request in 5.137751579284668s
Received healthy response to inference request in 1.680333137512207s
Received healthy response to inference request in 2.3552939891815186s
Received healthy response to inference request in 1.4602172374725342s
5 requests
0 failed requests
5th percentile: 1.482542085647583
10th percentile: 1.504866933822632
20th percentile: 1.5495166301727294
30th percentile: 1.5935398101806642
40th percentile: 1.6369364738464356
50th percentile: 1.680333137512207
60th percentile: 1.9503174781799315
70th percentile: 2.220301818847656
80th percentile: 2.911785507202149
90th percentile: 4.024768543243408
95th percentile: 4.581260061264038
99th percentile: 5.026453275680542
mean time: 2.441087484359741
Pipeline stage StressChecker completed in 32.40s
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 7.80s
Shutdown handler de-registered
cycy233-l3-p-v3-c4_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 cycy233-l3-p-v3-c4-v1-profiler
Waiting for inference service cycy233-l3-p-v3-c4-v1-profiler to be ready
Inference service cycy233-l3-p-v3-c4-v1-profiler ready after 170.42855429649353s
Pipeline stage MKMLProfilerDeployer completed in 170.79s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/cycy233-l3-p-v3-c4-v1-profiler-predictor-00001-deployment-zmq4g:/code/chaiverse_profiler_1726111364 --namespace tenant-chaiml-guanaco
kubectl exec -it cycy233-l3-p-v3-c4-v1-profiler-predictor-00001-deployment-zmq4g --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726111364 && python profiles.py profile --best_of_n 16 --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_1726111364/summary.json'
kubectl exec -it cycy233-l3-p-v3-c4-v1-profiler-predictor-00001-deployment-zmq4g --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726111364/summary.json'
Pipeline stage MKMLProfilerRunner completed in 843.90s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service cycy233-l3-p-v3-c4-v1-profiler is running
Tearing down inference service cycy233-l3-p-v3-c4-v1-profiler
Service cycy233-l3-p-v3-c4-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.17s
Shutdown handler de-registered
cycy233-l3-p-v3-c4_v1 status is now inactive due to auto deactivation removed underperforming models