submission_id: rica40325-spin-second_v2
developer_uid: rica40325
best_of: 8
celo_rating: 1256.63
display_name: rica40325-spin-second_v1
family_friendly_score: 0.0
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}
generation_params: {'temperature': 1.15, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: False
language_model: rica40325/spin_second
latencies: [{'batch_size': 1, 'throughput': 0.87303312999793, 'latency_mean': 1.1453622591495514, 'latency_p50': 1.153369426727295, 'latency_p90': 1.2554099082946777}, {'batch_size': 4, 'throughput': 1.888451785709152, 'latency_mean': 2.1047413182258605, 'latency_p50': 2.1117193698883057, 'latency_p90': 2.315593147277832}, {'batch_size': 5, 'throughput': 2.0546597562275375, 'latency_mean': 2.4224731504917143, 'latency_p50': 2.424053430557251, 'latency_p90': 2.6874738931655884}, {'batch_size': 8, 'throughput': 2.2715477317305823, 'latency_mean': 3.4997139489650726, 'latency_p50': 3.5215264558792114, 'latency_p90': 3.8939869880676268}, {'batch_size': 10, 'throughput': 2.33929865168226, 'latency_mean': 4.237554355859756, 'latency_p50': 4.261852383613586, 'latency_p90': 4.777291011810303}, {'batch_size': 12, 'throughput': 2.3857533432759253, 'latency_mean': 4.977639393806458, 'latency_p50': 5.004180073738098, 'latency_p90': 5.675149416923523}, {'batch_size': 15, 'throughput': 2.382432462019166, 'latency_mean': 6.215880420207977, 'latency_p50': 6.186755418777466, 'latency_p90': 6.989189219474793}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: rica40325/spin_second
model_name: rica40325-spin-second_v1
model_num_parameters: 8030261248.0
model_repo: rica40325/spin_second
model_size: 8B
num_battles: 13525
num_wins: 6841
ranking_group: single
status: torndown
submission_type: basic
throughput_3p7s: 2.31
timestamp: 2024-09-20T01:14:49+00:00
us_pacific_date: 2024-09-19
win_ratio: 0.5058040665434381
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 rica40325-spin-second-v2-mkmlizer
Waiting for job on rica40325-spin-second-v2-mkmlizer to finish
rica40325-spin-second-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-spin-second-v2-mkmlizer: ║ _____ __ __ ║
rica40325-spin-second-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rica40325-spin-second-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rica40325-spin-second-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rica40325-spin-second-v2-mkmlizer: ║ /___/ ║
rica40325-spin-second-v2-mkmlizer: ║ ║
rica40325-spin-second-v2-mkmlizer: ║ Version: 0.10.1 ║
rica40325-spin-second-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rica40325-spin-second-v2-mkmlizer: ║ https://mk1.ai ║
rica40325-spin-second-v2-mkmlizer: ║ ║
rica40325-spin-second-v2-mkmlizer: ║ The license key for the current software has been verified as ║
rica40325-spin-second-v2-mkmlizer: ║ belonging to: ║
rica40325-spin-second-v2-mkmlizer: ║ ║
rica40325-spin-second-v2-mkmlizer: ║ Chai Research Corp. ║
rica40325-spin-second-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rica40325-spin-second-v2-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
rica40325-spin-second-v2-mkmlizer: ║ ║
rica40325-spin-second-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
rica40325-spin-second-v2-mkmlizer: Downloaded to shared memory in 57.273s
rica40325-spin-second-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpz_b1n790, device:0
rica40325-spin-second-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rica40325-spin-second-v2-mkmlizer: quantized model in 28.598s
rica40325-spin-second-v2-mkmlizer: Processed model rica40325/spin_second in 85.871s
rica40325-spin-second-v2-mkmlizer: creating bucket guanaco-mkml-models
rica40325-spin-second-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-spin-second-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-spin-second-v2
rica40325-spin-second-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-spin-second-v2/config.json
rica40325-spin-second-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-spin-second-v2/flywheel_model.0.safetensors
rica40325-spin-second-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:10, 26.03it/s] Loading 0: 3%|▎ | 10/291 [00:00<00:08, 32.57it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:10, 25.96it/s] Loading 0: 7%|▋ | 21/291 [00:00<00:07, 36.34it/s] Loading 0: 9%|▉ | 26/291 [00:00<00:07, 35.85it/s] Loading 0: 11%|█ | 32/291 [00:00<00:06, 37.12it/s] Loading 0: 12%|█▏ | 36/291 [00:01<00:10, 25.12it/s] Loading 0: 14%|█▍ | 41/291 [00:01<00:09, 26.81it/s] Loading 0: 16%|█▋ | 48/291 [00:01<00:07, 34.26it/s] Loading 0: 18%|█▊ | 53/291 [00:01<00:06, 35.09it/s] Loading 0: 20%|█▉ | 58/291 [00:01<00:06, 35.96it/s] Loading 0: 21%|██▏ | 62/291 [00:01<00:06, 36.17it/s] Loading 0: 23%|██▎ | 66/291 [00:01<00:06, 37.06it/s] Loading 0: 24%|██▍ | 70/291 [00:02<00:06, 35.38it/s] Loading 0: 25%|██▌ | 74/291 [00:02<00:06, 35.62it/s] Loading 0: 27%|██▋ | 78/291 [00:02<00:06, 35.12it/s] Loading 0: 28%|██▊ | 82/291 [00:02<00:08, 24.83it/s] Loading 0: 29%|██▉ | 85/291 [00:02<00:08, 25.64it/s] Loading 0: 31%|███ | 90/291 [00:02<00:06, 30.68it/s] Loading 0: 32%|███▏ | 94/291 [00:02<00:06, 30.96it/s] Loading 0: 34%|███▍ | 99/291 [00:03<00:05, 33.85it/s] Loading 0: 35%|███▌ | 103/291 [00:03<00:05, 31.96it/s] Loading 0: 37%|███▋ | 108/291 [00:03<00:05, 34.07it/s] Loading 0: 38%|███▊ | 112/291 [00:03<00:05, 32.29it/s] Loading 0: 40%|███▉ | 116/291 [00:03<00:05, 31.92it/s] Loading 0: 42%|████▏ | 122/291 [00:03<00:04, 36.06it/s] Loading 0: 44%|████▎ | 127/291 [00:03<00:04, 34.51it/s] Loading 0: 46%|████▌ | 133/291 [00:04<00:05, 30.41it/s] Loading 0: 47%|████▋ | 137/291 [00:04<00:05, 30.39it/s] Loading 0: 48%|████▊ | 141/291 [00:04<00:05, 28.44it/s] Loading 0: 50%|████▉ | 145/291 [00:04<00:04, 30.73it/s] Loading 0: 51%|█████ | 149/291 [00:04<00:05, 27.95it/s] Loading 0: 54%|█████▎ | 156/291 [00:04<00:03, 35.54it/s] Loading 0: 55%|█████▍ | 160/291 [00:04<00:03, 33.91it/s] Loading 0: 57%|█████▋ | 165/291 [00:05<00:03, 36.86it/s] Loading 0: 58%|█████▊ | 169/291 [00:05<00:03, 35.20it/s] Loading 0: 60%|█████▉ | 174/291 [00:05<00:03, 36.96it/s] Loading 0: 61%|██████ | 178/291 [00:05<00:03, 34.80it/s] Loading 0: 63%|██████▎ | 184/291 [00:05<00:02, 40.91it/s] Loading 0: 65%|██████▍ | 189/291 [00:05<00:04, 23.87it/s] Loading 0: 67%|██████▋ | 194/291 [00:06<00:03, 25.13it/s] Loading 0: 69%|██████▉ | 201/291 [00:06<00:02, 31.48it/s] Loading 0: 70%|███████ | 205/291 [00:06<00:02, 31.04it/s] Loading 0: 72%|███████▏ | 209/291 [00:06<00:02, 32.28it/s] Loading 0: 73%|███████▎ | 213/291 [00:06<00:02, 29.32it/s] Loading 0: 75%|███████▌ | 219/291 [00:06<00:02, 34.37it/s] Loading 0: 77%|███████▋ | 223/291 [00:06<00:02, 32.83it/s] Loading 0: 78%|███████▊ | 227/291 [00:07<00:01, 32.55it/s] Loading 0: 79%|███████▉ | 231/291 [00:07<00:01, 31.46it/s] Loading 0: 81%|████████ | 235/291 [00:07<00:02, 24.89it/s] Loading 0: 82%|████████▏ | 239/291 [00:07<00:02, 24.41it/s] Loading 0: 85%|████████▍ | 246/291 [00:07<00:01, 31.50it/s] Loading 0: 86%|████████▌ | 250/291 [00:07<00:01, 31.02it/s] Loading 0: 88%|████████▊ | 255/291 [00:08<00:01, 34.02it/s] Loading 0: 89%|████████▉ | 259/291 [00:08<00:00, 32.64it/s] Loading 0: 91%|█████████ | 264/291 [00:08<00:00, 35.85it/s] Loading 0: 92%|█████████▏| 268/291 [00:08<00:00, 34.39it/s] Loading 0: 94%|█████████▍| 273/291 [00:08<00:00, 37.05it/s] Loading 0: 95%|█████████▌| 277/291 [00:08<00:00, 34.97it/s] Loading 0: 97%|█████████▋| 281/291 [00:08<00:00, 35.06it/s] Loading 0: 98%|█████████▊| 286/291 [00:14<00:01, 2.61it/s] Loading 0: 99%|█████████▉| 289/291 [00:14<00:00, 3.25it/s]
Job rica40325-spin-second-v2-mkmlizer completed after 104.85s with status: succeeded
Stopping job with name rica40325-spin-second-v2-mkmlizer
Pipeline stage MKMLizer completed in 105.84s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rica40325-spin-second-v2
Waiting for inference service rica40325-spin-second-v2 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
Inference service rica40325-spin-second-v2 ready after 383.28390192985535s
Pipeline stage MKMLDeployer completed in 383.78s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8126730918884277s
Received healthy response to inference request in 1.9533562660217285s
Received healthy response to inference request in 1.9273059368133545s
Received healthy response to inference request in 1.5825777053833008s
Received healthy response to inference request in 1.3142077922821045s
5 requests
0 failed requests
5th percentile: 1.3678817749023438
10th percentile: 1.421555757522583
20th percentile: 1.5289037227630615
30th percentile: 1.6285967826843262
40th percentile: 1.720634937286377
50th percentile: 1.8126730918884277
60th percentile: 1.8585262298583984
70th percentile: 1.9043793678283691
80th percentile: 1.9325160026550292
90th percentile: 1.9429361343383789
95th percentile: 1.9481462001800538
99th percentile: 1.9523142528533937
mean time: 1.7180241584777831
Pipeline stage StressChecker completed in 9.39s
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 7.53s
Shutdown handler de-registered
rica40325-spin-second_v2 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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rica40325-spin-second-v2-profiler
Waiting for inference service rica40325-spin-second-v2-profiler to be ready
Inference service rica40325-spin-second-v2-profiler ready after 210.50204396247864s
Pipeline stage MKMLProfilerDeployer completed in 210.86s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rica40325-spin-second-v2-profiler-predictor-00001-deploymepcm65:/code/chaiverse_profiler_1726795657 --namespace tenant-chaiml-guanaco
kubectl exec -it rica40325-spin-second-v2-profiler-predictor-00001-deploymepcm65 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726795657 && python profiles.py profile --best_of_n 8 --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 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1726795657/summary.json'
kubectl exec -it rica40325-spin-second-v2-profiler-predictor-00001-deploymepcm65 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726795657/summary.json'
Pipeline stage MKMLProfilerRunner completed in 779.28s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rica40325-spin-second-v2-profiler is running
Tearing down inference service rica40325-spin-second-v2-profiler
Service rica40325-spin-second-v2-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.02s
Shutdown handler de-registered
rica40325-spin-second_v2 status is now inactive due to auto deactivation removed underperforming models
rica40325-spin-second_v2 status is now torndown due to DeploymentManager action