submission_id: trace2333-fd-ultra-dl-axo-ep1_v1
developer_uid: Trace2333
alignment_samples: 11880
alignment_score: 0.6602368788008489
best_of: 16
celo_rating: 1211.1
display_name: trace2333-fd-ultra-dl-axo-ep1_v1
formatter: {'memory_template': "<|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\nYou: {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': 1.0, 'min_p': 0.0, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
is_internal_developer: False
language_model: Trace2333/fd_ultra_dl_axo_ep1
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: Trace2333/fd_ultra_dl_ax
model_name: trace2333-fd-ultra-dl-axo-ep1_v1
model_num_parameters: 8030261248.0
model_repo: Trace2333/fd_ultra_dl_axo_ep1
model_size: 8B
num_battles: 11879
num_wins: 5494
propriety_score: 0.7327235772357723
propriety_total_count: 984.0
ranking_group: single
status: inactive
submission_type: basic
timestamp: 2024-09-03T11:47:24+00:00
us_pacific_date: 2024-09-03
win_ratio: 0.4624968431686169
Download Preference Data
Resubmit model
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name trace2333-fd-ultra-dl-axo-ep1-v1-mkmlizer
Waiting for job on trace2333-fd-ultra-dl-axo-ep1-v1-mkmlizer to finish
trace2333-fd-ultra-dl-axo-ep1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-fd-ultra-dl-axo-ep1-v1-mkmlizer: ║ _____ __ __ ║
trace2333-fd-ultra-dl-axo-ep1-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
trace2333-fd-ultra-dl-axo-ep1-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
trace2333-fd-ultra-dl-axo-ep1-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
trace2333-fd-ultra-dl-axo-ep1-v1-mkmlizer: ║ /___/ ║
trace2333-fd-ultra-dl-axo-ep1-v1-mkmlizer: ║ ║
trace2333-fd-ultra-dl-axo-ep1-v1-mkmlizer: ║ Version: 0.10.1 ║
trace2333-fd-ultra-dl-axo-ep1-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
trace2333-fd-ultra-dl-axo-ep1-v1-mkmlizer: ║ https://mk1.ai ║
trace2333-fd-ultra-dl-axo-ep1-v1-mkmlizer: ║ ║
trace2333-fd-ultra-dl-axo-ep1-v1-mkmlizer: ║ The license key for the current software has been verified as ║
trace2333-fd-ultra-dl-axo-ep1-v1-mkmlizer: ║ belonging to: ║
trace2333-fd-ultra-dl-axo-ep1-v1-mkmlizer: ║ ║
trace2333-fd-ultra-dl-axo-ep1-v1-mkmlizer: ║ Chai Research Corp. ║
trace2333-fd-ultra-dl-axo-ep1-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
trace2333-fd-ultra-dl-axo-ep1-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
trace2333-fd-ultra-dl-axo-ep1-v1-mkmlizer: ║ ║
trace2333-fd-ultra-dl-axo-ep1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
trace2333-fd-ultra-dl-axo-ep1-v1-mkmlizer: Downloaded to shared memory in 63.504s
trace2333-fd-ultra-dl-axo-ep1-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpjsbnivaz, device:0
trace2333-fd-ultra-dl-axo-ep1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-fd-ultra-dl-axo-ep1-v1-mkmlizer: quantized model in 28.227s
trace2333-fd-ultra-dl-axo-ep1-v1-mkmlizer: Processed model Trace2333/fd_ultra_dl_axo_ep1 in 91.731s
trace2333-fd-ultra-dl-axo-ep1-v1-mkmlizer: creating bucket guanaco-mkml-models
trace2333-fd-ultra-dl-axo-ep1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-fd-ultra-dl-axo-ep1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-fd-ultra-dl-axo-ep1-v1
trace2333-fd-ultra-dl-axo-ep1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-fd-ultra-dl-axo-ep1-v1/config.json
trace2333-fd-ultra-dl-axo-ep1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-fd-ultra-dl-axo-ep1-v1/special_tokens_map.json
trace2333-fd-ultra-dl-axo-ep1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-fd-ultra-dl-axo-ep1-v1/tokenizer_config.json
trace2333-fd-ultra-dl-axo-ep1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-fd-ultra-dl-axo-ep1-v1/tokenizer.json
trace2333-fd-ultra-dl-axo-ep1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-fd-ultra-dl-axo-ep1-v1/flywheel_model.0.safetensors
trace2333-fd-ultra-dl-axo-ep1-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:10, 26.90it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:06, 43.76it/s] Loading 0: 6%|▌ | 17/291 [00:00<00:06, 40.48it/s] Loading 0: 8%|▊ | 22/291 [00:00<00:06, 39.78it/s] Loading 0: 9%|▉ | 27/291 [00:00<00:06, 41.33it/s] Loading 0: 11%|█ | 32/291 [00:00<00:06, 40.38it/s] Loading 0: 13%|█▎ | 37/291 [00:01<00:09, 25.86it/s] Loading 0: 14%|█▍ | 41/291 [00:01<00:09, 26.32it/s] Loading 0: 17%|█▋ | 49/291 [00:01<00:06, 34.88it/s] Loading 0: 19%|█▊ | 54/291 [00:01<00:06, 37.68it/s] Loading 0: 20%|██ | 59/291 [00:01<00:07, 33.01it/s] Loading 0: 23%|██▎ | 67/291 [00:01<00:05, 40.37it/s] Loading 0: 25%|██▍ | 72/291 [00:01<00:05, 41.97it/s] Loading 0: 26%|██▋ | 77/291 [00:02<00:05, 37.71it/s] Loading 0: 28%|██▊ | 82/291 [00:02<00:07, 29.62it/s] Loading 0: 30%|██▉ | 86/291 [00:02<00:06, 31.13it/s] Loading 0: 31%|███▏ | 91/291 [00:02<00:06, 32.81it/s] Loading 0: 33%|███▎ | 95/291 [00:02<00:05, 33.73it/s] Loading 0: 34%|███▍ | 100/291 [00:02<00:05, 35.00it/s] Loading 0: 36%|███▌ | 105/291 [00:02<00:04, 38.00it/s] Loading 0: 37%|███▋ | 109/291 [00:03<00:04, 36.63it/s] Loading 0: 39%|███▉ | 113/291 [00:03<00:04, 35.65it/s] Loading 0: 41%|████ | 118/291 [00:03<00:04, 38.53it/s] Loading 0: 42%|████▏ | 122/291 [00:03<00:04, 37.10it/s] Loading 0: 44%|████▎ | 127/291 [00:03<00:04, 33.90it/s] Loading 0: 46%|████▌ | 133/291 [00:03<00:05, 29.06it/s] Loading 0: 47%|████▋ | 137/291 [00:04<00:05, 28.79it/s] Loading 0: 48%|████▊ | 141/291 [00:04<00:05, 27.79it/s] Loading 0: 51%|█████ | 147/291 [00:04<00:04, 33.59it/s] Loading 0: 52%|█████▏ | 151/291 [00:04<00:04, 33.13it/s] Loading 0: 54%|█████▎ | 156/291 [00:04<00:03, 36.72it/s] Loading 0: 55%|█████▍ | 160/291 [00:04<00:03, 35.58it/s] Loading 0: 57%|█████▋ | 165/291 [00:04<00:03, 38.02it/s] Loading 0: 58%|█████▊ | 169/291 [00:04<00:03, 35.89it/s] Loading 0: 60%|█████▉ | 174/291 [00:04<00:03, 38.42it/s] Loading 0: 61%|██████ | 178/291 [00:05<00:03, 36.39it/s] Loading 0: 63%|██████▎ | 184/291 [00:05<00:02, 41.91it/s] Loading 0: 65%|██████▍ | 189/291 [00:05<00:04, 24.94it/s] Loading 0: 67%|██████▋ | 194/291 [00:05<00:03, 26.38it/s] Loading 0: 69%|██████▉ | 201/291 [00:05<00:02, 33.47it/s] Loading 0: 71%|███████ | 206/291 [00:06<00:02, 34.33it/s] Loading 0: 72%|███████▏ | 210/291 [00:06<00:02, 35.36it/s] Loading 0: 74%|███████▎ | 214/291 [00:06<00:02, 34.10it/s] Loading 0: 75%|███████▌ | 219/291 [00:06<00:01, 37.42it/s] Loading 0: 77%|███████▋ | 224/291 [00:06<00:01, 37.15it/s] Loading 0: 78%|███████▊ | 228/291 [00:06<00:02, 29.49it/s] Loading 0: 80%|████████ | 233/291 [00:06<00:02, 26.93it/s] Loading 0: 82%|████████▏ | 238/291 [00:07<00:01, 31.07it/s] Loading 0: 83%|████████▎ | 242/291 [00:07<00:01, 32.30it/s] Loading 0: 85%|████████▍ | 246/291 [00:07<00:01, 34.05it/s] Loading 0: 86%|████████▌ | 250/291 [00:07<00:01, 33.59it/s] Loading 0: 88%|████████▊ | 255/291 [00:07<00:00, 37.26it/s] Loading 0: 89%|████████▉ | 259/291 [00:07<00:00, 35.47it/s] Loading 0: 91%|█████████ | 264/291 [00:07<00:00, 38.47it/s] Loading 0: 92%|█████████▏| 268/291 [00:07<00:00, 36.21it/s] Loading 0: 94%|█████████▍| 273/291 [00:07<00:00, 38.36it/s] Loading 0: 95%|█████████▌| 277/291 [00:08<00:00, 36.30it/s] Loading 0: 97%|█████████▋| 281/291 [00:08<00:00, 36.99it/s] Loading 0: 98%|█████████▊| 286/291 [00:13<00:01, 2.60it/s] Loading 0: 99%|█████████▉| 289/291 [00:13<00:00, 3.24it/s]
Job trace2333-fd-ultra-dl-axo-ep1-v1-mkmlizer completed after 117.6s with status: succeeded
Stopping job with name trace2333-fd-ultra-dl-axo-ep1-v1-mkmlizer
Pipeline stage MKMLizer completed in 118.55s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service trace2333-fd-ultra-dl-axo-ep1-v1
Waiting for inference service trace2333-fd-ultra-dl-axo-ep1-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
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 trace2333-fd-ultra-dl-axo-ep1-v1 ready after 151.2226083278656s
Pipeline stage MKMLDeployer completed in 151.73s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1759657859802246s
Received healthy response to inference request in 1.6552989482879639s
Received healthy response to inference request in 1.8789494037628174s
Received healthy response to inference request in 1.8162939548492432s
Received healthy response to inference request in 1.9203543663024902s
5 requests
0 failed requests
5th percentile: 1.6874979496002198
10th percentile: 1.7196969509124755
20th percentile: 1.7840949535369872
30th percentile: 1.828825044631958
40th percentile: 1.8538872241973876
50th percentile: 1.8789494037628174
60th percentile: 1.8955113887786865
70th percentile: 1.9120733737945557
80th percentile: 1.9714766502380372
90th percentile: 2.0737212181091307
95th percentile: 2.1248435020446776
99th percentile: 2.165741329193115
mean time: 1.8893724918365478
Pipeline stage StressChecker completed in 10.41s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
starting trigger_guanaco_pipeline %s
Pipeline stage TriggerMKMLProfilingPipeline completed in 5.15s
trace2333-fd-ultra-dl-axo-ep1_v1 status is now deployed due to DeploymentManager action
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 0.15s
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 trace2333-fd-ultra-dl-axo-ep1-v1-profiler
Waiting for inference service trace2333-fd-ultra-dl-axo-ep1-v1-profiler to be ready
Inference service trace2333-fd-ultra-dl-axo-ep1-v1-profiler ready after 150.43049716949463s
Pipeline stage MKMLProfilerDeployer completed in 150.91s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/trace2333-fd-ultra-dfe6d86b00ad8e645f5ca4b5393f52a42-deplopmztq:/code/chaiverse_profiler_1725364526 --namespace tenant-chaiml-guanaco
kubectl exec -it trace2333-fd-ultra-dfe6d86b00ad8e645f5ca4b5393f52a42-deplopmztq --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725364526 && chmod +x profiles.py && python profiles.py profile --best_of_n 16 --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_1725364526/summary.json'
trace2333-fd-ultra-dl-axo-ep1_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics