cycy233-l3-p-v5-c2

submission_id: cycy233-l3-p-v5-c2_v3

developer_uid: shiroe40

alignment_samples: 12700

alignment_score: -0.07719534605994258

best_of: 16

celo_rating: 1245.47

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-v5-c2

latencies: [{'batch_size': 1, 'throughput': 0.9204075585272153, 'latency_mean': 1.0864137089252472, 'latency_p50': 1.082565188407898, 'latency_p90': 1.2192970991134644}, {'batch_size': 4, 'throughput': 1.7724198703117522, 'latency_mean': 2.244091333150864, 'latency_p50': 2.246316075325012, 'latency_p90': 2.4988018035888673}, {'batch_size': 5, 'throughput': 1.8459707100978626, 'latency_mean': 2.6955285465717314, 'latency_p50': 2.6735353469848633, 'latency_p90': 3.00857994556427}, {'batch_size': 8, 'throughput': 1.9909028174133983, 'latency_mean': 3.977991360425949, 'latency_p50': 4.021289348602295, 'latency_p90': 4.498469591140747}, {'batch_size': 10, 'throughput': 2.008011129971435, 'latency_mean': 4.930131959915161, 'latency_p50': 4.85344660282135, 'latency_p90': 5.803889226913452}, {'batch_size': 12, 'throughput': 2.011167548226882, 'latency_mean': 5.877428393363953, 'latency_p50': 5.865553140640259, 'latency_p90': 6.8260112524032595}, {'batch_size': 15, 'throughput': 2.027340460292898, 'latency_mean': 7.253689836263657, 'latency_p50': 7.350670576095581, 'latency_p90': 8.014226818084717}]

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_group: cycy233/L3-p-v5-c2

model_name: auto

model_num_parameters: 8030261248.0

model_repo: cycy233/L3-p-v5-c2

model_size: 8B

num_battles: 12700

num_wins: 6233

propriety_score: 0.7387152777777778

propriety_total_count: 1152.0

ranking_group: single

status: inactive

submission_type: basic

throughput_3p7s: 1.99

timestamp: 2024-09-14T10:27:55+00:00

us_pacific_date: 2024-09-14

win_ratio: 0.49078740157480316

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-v5-c2-v3-mkmlizer
Waiting for job on cycy233-l3-p-v5-c2-v3-mkmlizer to finish
cycy233-l3-p-v5-c2-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-p-v5-c2-v3-mkmlizer: ║     _____            __           __                                ║
cycy233-l3-p-v5-c2-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-l3-p-v5-c2-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-l3-p-v5-c2-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-l3-p-v5-c2-v3-mkmlizer: ║       /___/                                                         ║
cycy233-l3-p-v5-c2-v3-mkmlizer: ║                                                                     ║
cycy233-l3-p-v5-c2-v3-mkmlizer: ║  Version: 0.10.1                                                    ║
cycy233-l3-p-v5-c2-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-l3-p-v5-c2-v3-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-l3-p-v5-c2-v3-mkmlizer: ║                                                                     ║
cycy233-l3-p-v5-c2-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-l3-p-v5-c2-v3-mkmlizer: ║  belonging to:                                                      ║
cycy233-l3-p-v5-c2-v3-mkmlizer: ║                                                                     ║
cycy233-l3-p-v5-c2-v3-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-l3-p-v5-c2-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-l3-p-v5-c2-v3-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
cycy233-l3-p-v5-c2-v3-mkmlizer: ║                                                                     ║
cycy233-l3-p-v5-c2-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-p-v5-c2-v3-mkmlizer: Downloaded to shared memory in 35.994s
cycy233-l3-p-v5-c2-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpld4ykag7, device:0
cycy233-l3-p-v5-c2-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-p-v5-c2-v3-mkmlizer: quantized model in 26.208s
cycy233-l3-p-v5-c2-v3-mkmlizer: Processed model cycy233/L3-p-v5-c2 in 62.203s
cycy233-l3-p-v5-c2-v3-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-p-v5-c2-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-p-v5-c2-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-p-v5-c2-v3
cycy233-l3-p-v5-c2-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-p-v5-c2-v3/config.json
cycy233-l3-p-v5-c2-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-p-v5-c2-v3/special_tokens_map.json
cycy233-l3-p-v5-c2-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-p-v5-c2-v3/tokenizer_config.json
cycy233-l3-p-v5-c2-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-p-v5-c2-v3/tokenizer.json
cycy233-l3-p-v5-c2-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-p-v5-c2-v3/flywheel_model.0.safetensors
cycy233-l3-p-v5-c2-v3-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 4/291 [00:00<00:07, 39.13it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:04, 68.30it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:03, 73.88it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:03, 70.04it/s]
Loading 0:  15%|█▍        | 43/291 [00:00<00:03, 75.79it/s]
Loading 0:  20%|█▉        | 58/291 [00:00<00:02, 87.82it/s]
Loading 0:  24%|██▍       | 70/291 [00:00<00:02, 85.59it/s]
Loading 0:  29%|██▊       | 83/291 [00:01<00:07, 27.00it/s]
Loading 0:  31%|███       | 90/291 [00:02<00:06, 30.58it/s]
Loading 0:  33%|███▎      | 97/291 [00:02<00:05, 34.51it/s]
Loading 0:  36%|███▋      | 106/291 [00:02<00:04, 41.56it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:03, 49.04it/s]
Loading 0:  43%|████▎     | 124/291 [00:02<00:02, 56.72it/s]
Loading 0:  48%|████▊     | 139/291 [00:02<00:02, 67.16it/s]
Loading 0:  51%|█████     | 148/291 [00:02<00:02, 69.00it/s]
Loading 0:  54%|█████▍    | 157/291 [00:02<00:01, 70.35it/s]
Loading 0:  57%|█████▋    | 166/291 [00:03<00:01, 67.45it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:01, 66.91it/s]
Loading 0:  63%|██████▎   | 184/291 [00:03<00:01, 71.47it/s]
Loading 0:  66%|██████▌   | 192/291 [00:04<00:04, 21.53it/s]
Loading 0:  68%|██████▊   | 198/291 [00:04<00:03, 25.05it/s]
Loading 0:  70%|███████   | 205/291 [00:04<00:02, 30.10it/s]
Loading 0:  76%|███████▌  | 220/291 [00:04<00:01, 44.84it/s]
Loading 0:  80%|███████▉  | 232/291 [00:04<00:01, 52.57it/s]
Loading 0:  83%|████████▎ | 241/291 [00:05<00:00, 59.02it/s]
Loading 0:  86%|████████▌ | 250/291 [00:05<00:00, 62.04it/s]
Loading 0:  89%|████████▉ | 259/291 [00:05<00:00, 61.97it/s]
Loading 0:  92%|█████████▏| 268/291 [00:05<00:00, 63.73it/s]
Loading 0:  95%|█████████▌| 277/291 [00:05<00:00, 69.37it/s]
Loading 0:  99%|█████████▊| 287/291 [00:05<00:00, 43.40it/s]
                                                            
Job cycy233-l3-p-v5-c2-v3-mkmlizer completed after 85.08s with status: succeeded
Stopping job with name cycy233-l3-p-v5-c2-v3-mkmlizer
Pipeline stage MKMLizer completed in 86.46s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.07s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cycy233-l3-p-v5-c2-v3
Waiting for inference service cycy233-l3-p-v5-c2-v3 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
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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service cycy233-l3-p-v5-c2-v3 ready after 170.59673762321472s
Pipeline stage MKMLDeployer completed in 171.58s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4650826454162598s
Received healthy response to inference request in 1.6098601818084717s
Received healthy response to inference request in 2.2325432300567627s
Received healthy response to inference request in 3.2121939659118652s
Received healthy response to inference request in 1.9624767303466797s
5 requests
0 failed requests
5th percentile: 1.6803834915161133
10th percentile: 1.750906801223755
20th percentile: 1.891953420639038
30th percentile: 2.016490030288696
40th percentile: 2.1245166301727294
50th percentile: 2.2325432300567627
60th percentile: 2.3255589962005616
70th percentile: 2.4185747623443605
80th percentile: 2.614504909515381
90th percentile: 2.913349437713623
95th percentile: 3.062771701812744
99th percentile: 3.182309513092041
mean time: 2.2964313507080076
Pipeline stage StressChecker completed in 16.63s
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
cycy233-l3-p-v5-c2_v3 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 cycy233-l3-p-v5-c2-v3-profiler
Waiting for inference service cycy233-l3-p-v5-c2-v3-profiler to be ready
Inference service cycy233-l3-p-v5-c2-v3-profiler ready after 170.4098403453827s
Pipeline stage MKMLProfilerDeployer completed in 170.76s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/cycy233-l3-p-v5-c2-v3-profiler-predictor-00001-deployment-844hx:/code/chaiverse_profiler_1726310165 --namespace tenant-chaiml-guanaco
kubectl exec -it cycy233-l3-p-v5-c2-v3-profiler-predictor-00001-deployment-844hx --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726310165 && 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_1726310165/summary.json'
kubectl exec -it cycy233-l3-p-v5-c2-v3-profiler-predictor-00001-deployment-844hx --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726310165/summary.json'
Pipeline stage MKMLProfilerRunner completed in 846.27s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service cycy233-l3-p-v5-c2-v3-profiler is running
Tearing down inference service cycy233-l3-p-v5-c2-v3-profiler
Service cycy233-l3-p-v5-c2-v3-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.94s
Shutdown handler de-registered
cycy233-l3-p-v5-c2_v3 status is now inactive due to auto deactivation removed underperforming models