submission_id: closedcharacter-peach-9b_3442_v2
developer_uid: realhusoyun
best_of: 4
celo_rating: 1178.12
display_name: season-2-model
family_friendly_score: 0.0
formatter: {'memory_template': "### Instruction:\nAs the assistant, your task is to fully embody the given character, creating immersive, captivating narratives. Stay true to the character's personality and background, generating responses that not only reflect their core traits but are also accurate to their character. You are an expert actor that can fully immerse yourself into any role given.You do not break character for any reason, even if someone tries addressing you as an AI or language model.\nYour character: {bot_name}, which is described in detail below. As .\nContext: {memory}\n continue the exchange with {{user}}.This conversation is a dance, always continuing, always evolving.\nYour character: {bot_name}.\nContext: {memory}\n", 'prompt_template': '### Input:\n{prompt}\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '### Response:\n{bot_name}:', 'truncate_by_message': False}
generation_params: {'temperature': 1.22, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '<|im_end|>'], 'max_input_tokens': 2048, 'best_of': 4, 'max_output_tokens': 64}
gpu_counts: {'NVIDIA RTX A5000': 1}
ineligible_reason: num_battles<5000
is_internal_developer: False
language_model: ClosedCharacter/Peach-9B-8k-Roleplay
latencies: [{'batch_size': 1, 'throughput': 0.6178350001476237, 'latency_mean': 1.618489396572113, 'latency_p50': 1.6112505197525024, 'latency_p90': 1.7613784790039062}, {'batch_size': 3, 'throughput': 1.0999123276855325, 'latency_mean': 2.7222508800029757, 'latency_p50': 2.723807692527771, 'latency_p90': 3.0422242403030397}, {'batch_size': 5, 'throughput': 1.3322138275700577, 'latency_mean': 3.747485165596008, 'latency_p50': 3.7234569787979126, 'latency_p90': 4.249977803230285}, {'batch_size': 6, 'throughput': 1.3827766147064857, 'latency_mean': 4.312811126708985, 'latency_p50': 4.306811213493347, 'latency_p90': 4.861848855018616}, {'batch_size': 8, 'throughput': 1.4588445266736265, 'latency_mean': 5.459355882406235, 'latency_p50': 5.461109399795532, 'latency_p90': 6.176640272140503}, {'batch_size': 10, 'throughput': 1.4927125097757086, 'latency_mean': 6.651002957820892, 'latency_p50': 6.572013020515442, 'latency_p90': 7.49233181476593}]
max_input_tokens: 2048
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: ClosedCharacter/Peach-9B
model_name: season-2-model
model_num_parameters: 8829407232.0
model_repo: ClosedCharacter/Peach-9B-8k-Roleplay
model_size: 9B
num_battles: 4382
num_wins: 1812
ranking_group: single
status: torndown
submission_type: basic
throughput_3p7s: 1.33
timestamp: 2024-09-24T12:28:08+00:00
us_pacific_date: 2024-09-24
win_ratio: 0.4135098128708352
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 closedcharacter-peach-9b-3442-v2-mkmlizer
Waiting for job on closedcharacter-peach-9b-3442-v2-mkmlizer to finish
closedcharacter-peach-9b-3442-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
closedcharacter-peach-9b-3442-v2-mkmlizer: ║ _____ __ __ ║
closedcharacter-peach-9b-3442-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
closedcharacter-peach-9b-3442-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
closedcharacter-peach-9b-3442-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
closedcharacter-peach-9b-3442-v2-mkmlizer: ║ /___/ ║
closedcharacter-peach-9b-3442-v2-mkmlizer: ║ ║
closedcharacter-peach-9b-3442-v2-mkmlizer: ║ Version: 0.10.1 ║
closedcharacter-peach-9b-3442-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
closedcharacter-peach-9b-3442-v2-mkmlizer: ║ https://mk1.ai ║
closedcharacter-peach-9b-3442-v2-mkmlizer: ║ ║
closedcharacter-peach-9b-3442-v2-mkmlizer: ║ The license key for the current software has been verified as ║
closedcharacter-peach-9b-3442-v2-mkmlizer: ║ belonging to: ║
closedcharacter-peach-9b-3442-v2-mkmlizer: ║ ║
closedcharacter-peach-9b-3442-v2-mkmlizer: ║ Chai Research Corp. ║
closedcharacter-peach-9b-3442-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
closedcharacter-peach-9b-3442-v2-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
closedcharacter-peach-9b-3442-v2-mkmlizer: ║ ║
closedcharacter-peach-9b-3442-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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
closedcharacter-peach-9b-3442-v2-mkmlizer: Downloaded to shared memory in 24.027s
closedcharacter-peach-9b-3442-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_jpu_9tp, device:0
closedcharacter-peach-9b-3442-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
closedcharacter-peach-9b-3442-v2-mkmlizer: quantized model in 25.199s
closedcharacter-peach-9b-3442-v2-mkmlizer: Processed model ClosedCharacter/Peach-9B-8k-Roleplay in 49.226s
closedcharacter-peach-9b-3442-v2-mkmlizer: creating bucket guanaco-mkml-models
closedcharacter-peach-9b-3442-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
closedcharacter-peach-9b-3442-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/closedcharacter-peach-9b-3442-v2
closedcharacter-peach-9b-3442-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/closedcharacter-peach-9b-3442-v2/special_tokens_map.json
closedcharacter-peach-9b-3442-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/closedcharacter-peach-9b-3442-v2/config.json
closedcharacter-peach-9b-3442-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/closedcharacter-peach-9b-3442-v2/tokenizer_config.json
closedcharacter-peach-9b-3442-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/closedcharacter-peach-9b-3442-v2/tokenizer.model
closedcharacter-peach-9b-3442-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/closedcharacter-peach-9b-3442-v2/tokenizer.json
closedcharacter-peach-9b-3442-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/closedcharacter-peach-9b-3442-v2/flywheel_model.0.safetensors
closedcharacter-peach-9b-3442-v2-mkmlizer: Loading 0: 0%| | 0/435 [00:00<?, ?it/s] Loading 0: 1%| | 5/435 [00:00<00:10, 39.55it/s] Loading 0: 3%|▎ | 14/435 [00:00<00:08, 50.78it/s] Loading 0: 5%|▌ | 23/435 [00:00<00:07, 53.41it/s] Loading 0: 7%|▋ | 32/435 [00:00<00:07, 54.32it/s] Loading 0: 9%|▉ | 39/435 [00:00<00:07, 53.28it/s] Loading 0: 11%|█ | 46/435 [00:00<00:06, 57.06it/s] Loading 0: 12%|█▏ | 52/435 [00:00<00:06, 55.10it/s] Loading 0: 14%|█▍ | 60/435 [00:01<00:06, 61.11it/s] Loading 0: 15%|█▌ | 67/435 [00:01<00:06, 56.92it/s] Loading 0: 17%|█▋ | 73/435 [00:01<00:06, 56.49it/s] Loading 0: 18%|█▊ | 79/435 [00:01<00:06, 52.93it/s] Loading 0: 20%|█▉ | 85/435 [00:01<00:06, 54.68it/s] Loading 0: 21%|██ | 92/435 [00:01<00:07, 48.92it/s] Loading 0: 23%|██▎ | 99/435 [00:01<00:06, 52.79it/s] Loading 0: 24%|██▍ | 105/435 [00:01<00:06, 52.74it/s] Loading 0: 26%|██▌ | 111/435 [00:02<00:07, 46.12it/s] Loading 0: 27%|██▋ | 116/435 [00:02<00:09, 32.91it/s] Loading 0: 28%|██▊ | 122/435 [00:02<00:08, 36.05it/s] Loading 0: 30%|██▉ | 130/435 [00:02<00:06, 44.59it/s] Loading 0: 31%|███▏ | 136/435 [00:02<00:07, 41.68it/s] Loading 0: 32%|███▏ | 141/435 [00:02<00:07, 41.16it/s] Loading 0: 34%|███▍ | 147/435 [00:03<00:06, 45.15it/s] Loading 0: 35%|███▍ | 152/435 [00:03<00:06, 45.87it/s] Loading 0: 36%|███▌ | 157/435 [00:03<00:06, 45.76it/s] Loading 0: 37%|███▋ | 163/435 [00:03<00:06, 42.88it/s] Loading 0: 39%|███▊ | 168/435 [00:03<00:06, 43.28it/s] Loading 0: 40%|████ | 175/435 [00:03<00:05, 49.31it/s] Loading 0: 42%|████▏ | 181/435 [00:03<00:05, 44.56it/s] Loading 0: 43%|████▎ | 186/435 [00:03<00:05, 43.63it/s] Loading 0: 44%|████▍ | 193/435 [00:04<00:04, 49.35it/s] Loading 0: 46%|████▌ | 199/435 [00:04<00:05, 45.17it/s] Loading 0: 47%|████▋ | 204/435 [00:04<00:05, 43.63it/s] Loading 0: 49%|████▊ | 211/435 [00:04<00:04, 48.75it/s] Loading 0: 50%|████▉ | 217/435 [00:04<00:04, 45.04it/s] Loading 0: 51%|█████ | 222/435 [00:04<00:04, 46.05it/s] Loading 0: 53%|█████▎ | 229/435 [00:04<00:04, 51.11it/s] Loading 0: 54%|█████▍ | 235/435 [00:04<00:04, 46.61it/s] Loading 0: 55%|█████▌ | 240/435 [00:05<00:04, 46.12it/s] Loading 0: 57%|█████▋ | 247/435 [00:05<00:04, 46.96it/s] Loading 0: 58%|█████▊ | 252/435 [00:05<00:05, 32.59it/s] Loading 0: 59%|█████▉ | 257/435 [00:05<00:05, 34.69it/s] Loading 0: 61%|██████ | 265/435 [00:05<00:03, 43.11it/s] Loading 0: 62%|██████▏ | 271/435 [00:05<00:03, 41.18it/s] Loading 0: 63%|██████▎ | 276/435 [00:05<00:03, 42.56it/s] Loading 0: 65%|██████▌ | 283/435 [00:06<00:03, 48.06it/s] Loading 0: 66%|██████▋ | 289/435 [00:06<00:03, 44.26it/s] Loading 0: 68%|██████▊ | 294/435 [00:06<00:03, 43.16it/s] Loading 0: 69%|██████▉ | 301/435 [00:06<00:02, 48.83it/s] Loading 0: 71%|███████ | 307/435 [00:06<00:02, 45.09it/s] Loading 0: 72%|███████▏ | 312/435 [00:06<00:02, 44.67it/s] Loading 0: 73%|███████▎ | 319/435 [00:06<00:02, 49.59it/s] Loading 0: 75%|███████▍ | 325/435 [00:07<00:02, 45.39it/s] Loading 0: 76%|███████▌ | 330/435 [00:07<00:02, 45.64it/s] Loading 0: 77%|███████▋ | 337/435 [00:07<00:01, 51.15it/s] Loading 0: 79%|███████▉ | 343/435 [00:07<00:02, 45.84it/s] Loading 0: 80%|████████ | 348/435 [00:07<00:01, 43.93it/s] Loading 0: 81%|████████▏ | 354/435 [00:07<00:01, 47.13it/s] Loading 0: 83%|████████▎ | 359/435 [00:07<00:01, 47.19it/s] Loading 0: 84%|████████▎ | 364/435 [00:07<00:01, 47.16it/s] Loading 0: 85%|████████▌ | 370/435 [00:08<00:01, 43.85it/s] Loading 0: 86%|████████▋ | 376/435 [00:10<00:09, 6.03it/s] Loading 0: 88%|████████▊ | 382/435 [00:10<00:06, 8.33it/s] Loading 0: 89%|████████▉ | 389/435 [00:11<00:03, 11.64it/s] Loading 0: 91%|█████████ | 396/435 [00:11<00:02, 15.98it/s] Loading 0: 92%|█████████▏| 401/435 [00:11<00:01, 18.90it/s] Loading 0: 93%|█████████▎| 406/435 [00:11<00:01, 22.56it/s] Loading 0: 94%|█████████▍| 411/435 [00:11<00:00, 24.82it/s] Loading 0: 97%|█████████▋| 420/435 [00:11<00:00, 32.58it/s] Loading 0: 98%|█████████▊| 428/435 [00:11<00:00, 40.35it/s] Loading 0: 100%|█████████▉| 434/435 [00:11<00:00, 42.38it/s]
Job closedcharacter-peach-9b-3442-v2-mkmlizer completed after 72.43s with status: succeeded
Stopping job with name closedcharacter-peach-9b-3442-v2-mkmlizer
Pipeline stage MKMLizer completed in 73.32s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.51s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service closedcharacter-peach-9b-3442-v2
Waiting for inference service closedcharacter-peach-9b-3442-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
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 closedcharacter-peach-9b-3442-v2 ready after 200.85398364067078s
Pipeline stage MKMLDeployer completed in 201.56s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.339003086090088s
Received healthy response to inference request in 3.0597426891326904s
Received healthy response to inference request in 2.5767340660095215s
Received healthy response to inference request in 2.7436249256134033s
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
Received healthy response to inference request in 2.5007054805755615s
5 requests
0 failed requests
5th percentile: 2.371343564987183
10th percentile: 2.4036840438842773
20th percentile: 2.4683650016784666
30th percentile: 2.5159111976623536
40th percentile: 2.5463226318359373
50th percentile: 2.5767340660095215
60th percentile: 2.6434904098510743
70th percentile: 2.710246753692627
80th percentile: 2.806848478317261
90th percentile: 2.9332955837249757
95th percentile: 2.996519136428833
99th percentile: 3.047097978591919
mean time: 2.643962049484253
Pipeline stage StressChecker completed in 14.70s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Failed to get response for submission blend_simib_2024-09-20: ('http://zonemercy-lexical-nemov8-5966-v9-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:52984->127.0.0.1:8080: read: connection reset by peer\n')
Pipeline stage TriggerMKMLProfilingPipeline completed in 10.43s
Shutdown handler de-registered
closedcharacter-peach-9b_3442_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 0.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service closedcharacter-peach-9b-3442-v2-profiler
Waiting for inference service closedcharacter-peach-9b-3442-v2-profiler to be ready
Inference service closedcharacter-peach-9b-3442-v2-profiler ready after 210.48757243156433s
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/closedcharacter-peac394bd6b446eee5bc0161d58802061db6-deplo5dv4l:/code/chaiverse_profiler_1727181448 --namespace tenant-chaiml-guanaco
kubectl exec -it closedcharacter-peac394bd6b446eee5bc0161d58802061db6-deplo5dv4l --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1727181448 && python profiles.py profile --best_of_n 4 --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 2048 --output_tokens 64 --summary /code/chaiverse_profiler_1727181448/summary.json'
kubectl exec -it closedcharacter-peac394bd6b446eee5bc0161d58802061db6-deplo5dv4l --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1727181448/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1076.46s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service closedcharacter-peach-9b-3442-v2-profiler is running
Tearing down inference service closedcharacter-peach-9b-3442-v2-profiler
Service closedcharacter-peach-9b-3442-v2-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.93s
Shutdown handler de-registered
closedcharacter-peach-9b_3442_v2 status is now inactive due to auto deactivation removed underperforming models
closedcharacter-peach-9b_3442_v2 status is now torndown due to DeploymentManager action