developer_uid: shiroe40
submission_id: cycy233-l3-bp-v4-c3_v2
model_name: auto
model_group: cycy233/L3-bp-v4-c3
status: torndown
timestamp: 2024-09-03T02:37:17+00:00
num_battles: 11192
num_wins: 5639
celo_rating: 1241.4
family_friendly_score: 0.0
submission_type: basic
model_repo: cycy233/L3-bp-v4-c3
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: auto
is_internal_developer: False
language_model: cycy233/L3-bp-v4-c3
model_size: 8B
ranking_group: single
us_pacific_date: 2024-09-02
win_ratio: 0.5038420300214439
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}
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}
Resubmit model
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-bp-v4-c3-v2-mkmlizer
Waiting for job on cycy233-l3-bp-v4-c3-v2-mkmlizer to finish
cycy233-l3-bp-v4-c3-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-bp-v4-c3-v2-mkmlizer: ║ _____ __ __ ║
cycy233-l3-bp-v4-c3-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-bp-v4-c3-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-bp-v4-c3-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-bp-v4-c3-v2-mkmlizer: ║ /___/ ║
cycy233-l3-bp-v4-c3-v2-mkmlizer: ║ ║
cycy233-l3-bp-v4-c3-v2-mkmlizer: ║ Version: 0.10.1 ║
cycy233-l3-bp-v4-c3-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-bp-v4-c3-v2-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-bp-v4-c3-v2-mkmlizer: ║ ║
cycy233-l3-bp-v4-c3-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-bp-v4-c3-v2-mkmlizer: ║ belonging to: ║
cycy233-l3-bp-v4-c3-v2-mkmlizer: ║ ║
cycy233-l3-bp-v4-c3-v2-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-bp-v4-c3-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-bp-v4-c3-v2-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-l3-bp-v4-c3-v2-mkmlizer: ║ ║
cycy233-l3-bp-v4-c3-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-bp-v4-c3-v2-mkmlizer: Downloaded to shared memory in 31.358s
cycy233-l3-bp-v4-c3-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp8ek9u2rm, device:0
cycy233-l3-bp-v4-c3-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-bp-v4-c3-v2-mkmlizer: quantized model in 25.494s
cycy233-l3-bp-v4-c3-v2-mkmlizer: Processed model cycy233/L3-bp-v4-c3 in 56.852s
cycy233-l3-bp-v4-c3-v2-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-bp-v4-c3-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-bp-v4-c3-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-bp-v4-c3-v2
cycy233-l3-bp-v4-c3-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-bp-v4-c3-v2/config.json
cycy233-l3-bp-v4-c3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-bp-v4-c3-v2/tokenizer_config.json
cycy233-l3-bp-v4-c3-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-bp-v4-c3-v2/special_tokens_map.json
cycy233-l3-bp-v4-c3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-bp-v4-c3-v2/tokenizer.json
cycy233-l3-bp-v4-c3-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-bp-v4-c3-v2/flywheel_model.0.safetensors
cycy233-l3-bp-v4-c3-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 7/291 [00:00<00:05, 49.66it/s] Loading 0: 8%|▊ | 22/291 [00:00<00:03, 87.13it/s] Loading 0: 12%|█▏ | 34/291 [00:00<00:02, 87.73it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:02, 97.53it/s] Loading 0: 21%|██ | 61/291 [00:00<00:02, 94.59it/s] Loading 0: 24%|██▍ | 71/291 [00:00<00:02, 96.08it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:07, 26.00it/s] Loading 0: 31%|███ | 90/291 [00:02<00:06, 29.71it/s] Loading 0: 35%|███▌ | 103/291 [00:02<00:04, 38.93it/s] Loading 0: 38%|███▊ | 112/291 [00:02<00:03, 45.40it/s] Loading 0: 43%|████▎ | 124/291 [00:02<00:03, 54.64it/s] Loading 0: 48%|████▊ | 139/291 [00:02<00:02, 66.63it/s] Loading 0: 51%|█████ | 148/291 [00:02<00:02, 70.96it/s] Loading 0: 54%|█████▍ | 157/291 [00:02<00:01, 72.96it/s] Loading 0: 58%|█████▊ | 169/291 [00:02<00:01, 75.31it/s] Loading 0: 63%|██████▎ | 184/291 [00:03<00:01, 84.61it/s] Loading 0: 67%|██████▋ | 194/291 [00:04<00:03, 26.36it/s] Loading 0: 69%|██████▉ | 202/291 [00:04<00:02, 31.13it/s] Loading 0: 74%|███████▎ | 214/291 [00:04<00:01, 39.20it/s] Loading 0: 79%|███████▊ | 229/291 [00:04<00:01, 51.22it/s] Loading 0: 82%|████████▏ | 238/291 [00:04<00:00, 55.92it/s] Loading 0: 85%|████████▍ | 247/291 [00:04<00:00, 59.55it/s] Loading 0: 88%|████████▊ | 256/291 [00:04<00:00, 63.86it/s] Loading 0: 92%|█████████▏| 267/291 [00:05<00:00, 73.60it/s] Loading 0: 95%|█████████▍| 276/291 [00:05<00:00, 76.26it/s] Loading 0: 98%|█████████▊| 285/291 [00:05<00:00, 78.20it/s]
Job cycy233-l3-bp-v4-c3-v2-mkmlizer completed after 75.51s with status: succeeded
Stopping job with name cycy233-l3-bp-v4-c3-v2-mkmlizer
Pipeline stage MKMLizer completed in 77.11s
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 cycy233-l3-bp-v4-c3-v2
Waiting for inference service cycy233-l3-bp-v4-c3-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
Inference service cycy233-l3-bp-v4-c3-v2 ready after 150.75626492500305s
Pipeline stage MKMLDeployer completed in 151.34s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.607393264770508s
Received healthy response to inference request in 1.7324507236480713s
Received healthy response to inference request in 1.6579492092132568s
Received healthy response to inference request in 1.553945541381836s
Received healthy response to inference request in 1.8611397743225098s
5 requests
0 failed requests
5th percentile: 1.57474627494812
10th percentile: 1.5955470085144043
20th percentile: 1.6371484756469727
30th percentile: 1.6728495121002198
40th percentile: 1.7026501178741456
50th percentile: 1.7324507236480713
60th percentile: 1.7839263439178468
70th percentile: 1.835401964187622
80th percentile: 2.0103904724121096
90th percentile: 2.3088918685913087
95th percentile: 2.458142566680908
99th percentile: 2.5775431251525878
mean time: 1.8825757026672363
Pipeline stage StressChecker completed in 10.96s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
starting trigger_guanaco_pipeline %s
Pipeline stage TriggerMKMLProfilingPipeline completed in 5.39s
cycy233-l3-bp-v4-c3_v2 status is now deployed due to DeploymentManager action
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cycy233-l3-bp-v4-c3-v2-profiler
Waiting for inference service cycy233-l3-bp-v4-c3-v2-profiler to be ready
Inference service cycy233-l3-bp-v4-c3-v2-profiler ready after 140.38998818397522s
Pipeline stage MKMLProfilerDeployer completed in 140.86s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/cycy233-l3-bp-v4-c3-v2-profiler-predictor-00001-deploymentd26g6:/code/chaiverse_profiler_1725331465 --namespace tenant-chaiml-guanaco
kubectl exec -it cycy233-l3-bp-v4-c3-v2-profiler-predictor-00001-deploymentd26g6 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725331465 && 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_1725331465/summary.json'
cycy233-l3-bp-v4-c3_v2 status is now inactive due to auto deactivation removed underperforming models
cycy233-l3-bp-v4-c3_v2 status is now torndown due to DeploymentManager action