chaiml-elite-feed-convo-_6421

submission_id: chaiml-elite-feed-convo-_6421_v2

developer_uid: zonemercy

alignment_samples: 11917

alignment_score: 0.3747599950243405

best_of: 8

celo_rating: 1257.49

display_name: chaiml-elite-feed-convo-_6421_v2

formatter: {'memory_template': "Bot's name: {bot_name}\n####\n", 'prompt_template': '', 'bot_template': 'Bot: {message}</s>', 'user_template': 'User: {message}</s>', 'response_template': 'Bot:', 'truncate_by_message': True}

generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['</s>', 'Bot:', 'User:', 'You:', '<|im_end|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

gpu_counts: {'NVIDIA RTX A5000': 1}

is_internal_developer: True

language_model: ChaiML/Elite-Feed-Convo-v3-1e5

latencies: [{'batch_size': 1, 'throughput': 0.613735097585569, 'latency_mean': 1.6293031680583954, 'latency_p50': 1.6377605199813843, 'latency_p90': 1.7987481355667114}, {'batch_size': 3, 'throughput': 1.0832378817432684, 'latency_mean': 2.7565170764923095, 'latency_p50': 2.7646225690841675, 'latency_p90': 3.0677417516708374}, {'batch_size': 5, 'throughput': 1.2457552514843033, 'latency_mean': 3.991032679080963, 'latency_p50': 4.010728716850281, 'latency_p90': 4.530212664604187}, {'batch_size': 6, 'throughput': 1.2508942936532588, 'latency_mean': 4.765424054861069, 'latency_p50': 4.769799470901489, 'latency_p90': 5.439401721954345}, {'batch_size': 8, 'throughput': 1.2433935203248208, 'latency_mean': 6.402462208271027, 'latency_p50': 6.410699844360352, 'latency_p90': 7.182159280776977}, {'batch_size': 10, 'throughput': 1.1830086137896487, 'latency_mean': 8.40642604112625, 'latency_p50': 8.396616339683533, 'latency_p90': 9.638114666938781}]

max_input_tokens: 1024

max_output_tokens: 64

model_architecture: MistralForCausalLM

model_group: ChaiML/Elite-Feed-Convo-

model_name: chaiml-elite-feed-convo-_6421_v2

model_num_parameters: 12772070400.0

model_repo: ChaiML/Elite-Feed-Convo-v3-1e5

model_size: 13B

num_battles: 11916

num_wins: 6227

propriety_score: 0.7327502429543246

propriety_total_count: 1029.0

ranking_group: single

status: inactive

submission_type: basic

throughput_3p7s: 1.22

timestamp: 2024-09-12T19:48:58+00:00

us_pacific_date: 2024-09-12

win_ratio: 0.5225746894931185

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 chaiml-elite-feed-convo-6421-v2-mkmlizer
Waiting for job on chaiml-elite-feed-convo-6421-v2-mkmlizer to finish
chaiml-elite-feed-convo-6421-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-elite-feed-convo-6421-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-elite-feed-convo-6421-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-elite-feed-convo-6421-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-elite-feed-convo-6421-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-elite-feed-convo-6421-v2-mkmlizer: ║       /___/                                                         ║
chaiml-elite-feed-convo-6421-v2-mkmlizer: ║                                                                     ║
chaiml-elite-feed-convo-6421-v2-mkmlizer: ║  Version: 0.10.1                                                    ║
chaiml-elite-feed-convo-6421-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-elite-feed-convo-6421-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-elite-feed-convo-6421-v2-mkmlizer: ║                                                                     ║
chaiml-elite-feed-convo-6421-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-elite-feed-convo-6421-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-elite-feed-convo-6421-v2-mkmlizer: ║                                                                     ║
chaiml-elite-feed-convo-6421-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-elite-feed-convo-6421-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-elite-feed-convo-6421-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-elite-feed-convo-6421-v2-mkmlizer: ║                                                                     ║
chaiml-elite-feed-convo-6421-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-elite-feed-convo-6421-v2-mkmlizer: Downloaded to shared memory in 32.471s
chaiml-elite-feed-convo-6421-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpw9z9tlyn, device:0
chaiml-elite-feed-convo-6421-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-elite-feed-convo-6421-v2-mkmlizer: quantized model in 35.592s
chaiml-elite-feed-convo-6421-v2-mkmlizer: Processed model ChaiML/Elite-Feed-Convo-v3-1e5 in 68.064s
chaiml-elite-feed-convo-6421-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-elite-feed-convo-6421-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-elite-feed-convo-6421-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-elite-feed-convo-6421-v2
chaiml-elite-feed-convo-6421-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-elite-feed-convo-6421-v2/config.json
chaiml-elite-feed-convo-6421-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-elite-feed-convo-6421-v2/special_tokens_map.json
chaiml-elite-feed-convo-6421-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-elite-feed-convo-6421-v2/tokenizer_config.json
chaiml-elite-feed-convo-6421-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-elite-feed-convo-6421-v2/tokenizer.json
chaiml-elite-feed-convo-6421-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-elite-feed-convo-6421-v2/flywheel_model.0.safetensors
chaiml-elite-feed-convo-6421-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 29.14it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 48.86it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:08, 42.23it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 40.86it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:07, 45.84it/s]
Loading 0:  10%|▉         | 35/363 [00:00<00:07, 46.69it/s]
Loading 0:  11%|█▏        | 41/363 [00:00<00:07, 41.90it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:06, 45.12it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:06, 48.08it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 37.53it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:07, 37.78it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:07, 40.30it/s]
Loading 0:  21%|██        | 76/363 [00:01<00:06, 42.09it/s]
Loading 0:  23%|██▎       | 82/363 [00:01<00:07, 39.29it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:05, 47.45it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:06, 43.28it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:06, 43.04it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:05, 44.10it/s]
Loading 0:  31%|███       | 112/363 [00:02<00:05, 47.68it/s]
Loading 0:  32%|███▏      | 117/363 [00:02<00:05, 46.59it/s]
Loading 0:  34%|███▎      | 122/363 [00:02<00:05, 46.70it/s]
Loading 0:  35%|███▍      | 127/363 [00:02<00:05, 40.36it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:04, 48.59it/s]
Loading 0:  39%|███▉      | 141/363 [00:03<00:04, 48.38it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 34.05it/s]
Loading 0:  42%|████▏     | 151/363 [00:03<00:06, 34.63it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:05, 39.49it/s]
Loading 0:  45%|████▍     | 162/363 [00:03<00:04, 40.82it/s]
Loading 0:  46%|████▌     | 167/363 [00:04<00:05, 36.00it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:04, 44.55it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:04, 41.77it/s]
Loading 0:  51%|█████     | 186/363 [00:04<00:04, 41.25it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 46.79it/s]
Loading 0:  55%|█████▍    | 198/363 [00:04<00:03, 46.04it/s]
Loading 0:  56%|█████▌    | 203/363 [00:04<00:04, 39.34it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:03, 47.46it/s]
Loading 0:  60%|█████▉    | 217/363 [00:05<00:03, 45.25it/s]
Loading 0:  61%|██████    | 222/363 [00:05<00:03, 46.04it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:04, 32.97it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:04, 31.97it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:03, 38.52it/s]
Loading 0:  67%|██████▋   | 243/363 [00:05<00:02, 40.86it/s]
Loading 0:  68%|██████▊   | 248/363 [00:06<00:03, 34.73it/s]
Loading 0:  70%|███████   | 255/363 [00:06<00:02, 42.22it/s]
Loading 0:  72%|███████▏  | 260/363 [00:06<00:02, 42.79it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 43.61it/s]
Loading 0:  74%|███████▍  | 270/363 [00:06<00:02, 44.15it/s]
Loading 0:  76%|███████▌  | 275/363 [00:06<00:02, 36.19it/s]
Loading 0:  78%|███████▊  | 282/363 [00:06<00:01, 43.89it/s]
Loading 0:  79%|███████▉  | 287/363 [00:06<00:01, 42.10it/s]
Loading 0:  80%|████████  | 292/363 [00:06<00:01, 43.21it/s]
Loading 0:  82%|████████▏ | 297/363 [00:07<00:01, 44.20it/s]
Loading 0:  83%|████████▎ | 303/363 [00:07<00:01, 42.93it/s]
Loading 0:  85%|████████▍ | 308/363 [00:14<00:22,  2.47it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:15,  3.20it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:08,  5.27it/s]
Loading 0:  90%|████████▉ | 325/363 [00:14<00:05,  6.92it/s]
Loading 0:  91%|█████████ | 330/363 [00:14<00:03,  8.81it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 13.43it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:01, 16.89it/s]
Loading 0:  96%|█████████▋| 350/363 [00:14<00:00, 21.13it/s]
Loading 0:  98%|█████████▊| 357/363 [00:15<00:00, 25.37it/s]
                                                            
Job chaiml-elite-feed-convo-6421-v2-mkmlizer completed after 96.17s with status: succeeded
Stopping job with name chaiml-elite-feed-convo-6421-v2-mkmlizer
Pipeline stage MKMLizer completed in 97.01s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-elite-feed-convo-6421-v2
Waiting for inference service chaiml-elite-feed-convo-6421-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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service chaiml-elite-feed-convo-6421-v2 ready after 170.9457631111145s
Pipeline stage MKMLDeployer completed in 171.64s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.461585760116577s
Received healthy response to inference request in 1.9329338073730469s
Received healthy response to inference request in 2.127117395401001s
Received healthy response to inference request in 1.993957757949829s
Received healthy response to inference request in 2.1919403076171875s
5 requests
0 failed requests
5th percentile: 1.9451385974884032
10th percentile: 1.9573433876037598
20th percentile: 1.9817529678344727
30th percentile: 2.0205896854400636
40th percentile: 2.073853540420532
50th percentile: 2.127117395401001
60th percentile: 2.1530465602874758
70th percentile: 2.17897572517395
80th percentile: 2.645869398117066
90th percentile: 3.5537275791168215
95th percentile: 4.007656669616699
99th percentile: 4.3707999420166015
mean time: 2.5415070056915283
Pipeline stage StressChecker completed in 13.54s
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 4.45s
Shutdown handler de-registered
chaiml-elite-feed-convo-_6421_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 0.11s
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 chaiml-elite-feed-convo-6421-v2-profiler
Waiting for inference service chaiml-elite-feed-convo-6421-v2-profiler to be ready
Inference service chaiml-elite-feed-convo-6421-v2-profiler ready after 180.4190616607666s
Pipeline stage MKMLProfilerDeployer completed in 180.79s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-elite-feed-co1198987b27b5da55c4dba9807a48c229-deplog6ft4:/code/chaiverse_profiler_1726171045 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-elite-feed-co1198987b27b5da55c4dba9807a48c229-deplog6ft4 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726171045 && 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_1726171045/summary.json'
kubectl exec -it chaiml-elite-feed-co1198987b27b5da55c4dba9807a48c229-deplog6ft4 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726171045/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1167.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-elite-feed-convo-6421-v2-profiler is running
Tearing down inference service chaiml-elite-feed-convo-6421-v2-profiler
Service chaiml-elite-feed-convo-6421-v2-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.11s
Shutdown handler de-registered
chaiml-elite-feed-convo-_6421_v2 status is now inactive due to auto deactivation removed underperforming models