rica40325-llama-onlygpt-mul

developer_uid: rica40325

submission_id: rica40325-llama-onlygpt-mul_v1

model_name: rica40325-llama-onlygpt-mul_v1

model_group: rica40325/llama_onlygpt_

status: torndown

timestamp: 2025-05-08T07:49:41+00:00

num_battles: 7532

num_wins: 3003

celo_rating: 1217.26

family_friendly_score: 0.6332

family_friendly_standard_error: 0.006815537542996884

submission_type: basic

model_repo: rica40325/llama_onlygpt_mul

model_architecture: LlamaForCausalLM

model_num_parameters: 8030261248.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.844710962339797, 'latency_mean': 1.1837657654285432, 'latency_p50': 1.1837652921676636, 'latency_p90': 1.3018904685974122}, {'batch_size': 4, 'throughput': 1.7552897717919156, 'latency_mean': 2.26689973115921, 'latency_p50': 2.241331696510315, 'latency_p90': 2.50333890914917}, {'batch_size': 5, 'throughput': 1.895686178873628, 'latency_mean': 2.627253543138504, 'latency_p50': 2.6194669008255005, 'latency_p90': 2.9213850259780885}, {'batch_size': 8, 'throughput': 2.1000933855455615, 'latency_mean': 3.784804266691208, 'latency_p50': 3.792028069496155, 'latency_p90': 4.229026842117309}, {'batch_size': 10, 'throughput': 2.144460048541095, 'latency_mean': 4.623282768726349, 'latency_p50': 4.64837646484375, 'latency_p90': 5.18663911819458}, {'batch_size': 12, 'throughput': 2.1665280969159, 'latency_mean': 5.486969046592712, 'latency_p50': 5.51711630821228, 'latency_p90': 6.240833401679993}, {'batch_size': 15, 'throughput': 2.1999222189270364, 'latency_mean': 6.729323046207428, 'latency_p50': 6.698392271995544, 'latency_p90': 7.641661167144775}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rica40325-llama-onlygpt-mul_v1

is_internal_developer: False

language_model: rica40325/llama_onlygpt_mul

model_size: 8B

ranking_group: single

throughput_3p7s: 2.1

us_pacific_date: 2025-05-08

win_ratio: 0.3986988847583643

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

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}

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-llama-onlygpt-mul-v1-mkmlizer
Waiting for job on rica40325-llama-onlygpt-mul-v1-mkmlizer to finish
rica40325-llama-onlygpt-mul-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-llama-onlygpt-mul-v1-mkmlizer: ║     _____            __           __                                ║
rica40325-llama-onlygpt-mul-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rica40325-llama-onlygpt-mul-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rica40325-llama-onlygpt-mul-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rica40325-llama-onlygpt-mul-v1-mkmlizer: ║       /___/                                                         ║
rica40325-llama-onlygpt-mul-v1-mkmlizer: ║                                                                     ║
rica40325-llama-onlygpt-mul-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rica40325-llama-onlygpt-mul-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rica40325-llama-onlygpt-mul-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rica40325-llama-onlygpt-mul-v1-mkmlizer: ║                                                                     ║
rica40325-llama-onlygpt-mul-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rica40325-llama-onlygpt-mul-v1-mkmlizer: ║  belonging to:                                                      ║
rica40325-llama-onlygpt-mul-v1-mkmlizer: ║                                                                     ║
rica40325-llama-onlygpt-mul-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rica40325-llama-onlygpt-mul-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rica40325-llama-onlygpt-mul-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rica40325-llama-onlygpt-mul-v1-mkmlizer: ║                                                                     ║
rica40325-llama-onlygpt-mul-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rica40325-llama-onlygpt-mul-v1-mkmlizer: Downloaded to shared memory in 28.050s
rica40325-llama-onlygpt-mul-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpr4_hra5p, device:0
rica40325-llama-onlygpt-mul-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rica40325-llama-onlygpt-mul-v1-mkmlizer: quantized model in 26.752s
rica40325-llama-onlygpt-mul-v1-mkmlizer: Processed model rica40325/llama_onlygpt_mul in 54.804s
rica40325-llama-onlygpt-mul-v1-mkmlizer: creating bucket guanaco-mkml-models
rica40325-llama-onlygpt-mul-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-llama-onlygpt-mul-v1/config.json
rica40325-llama-onlygpt-mul-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-llama-onlygpt-mul-v1/special_tokens_map.json
rica40325-llama-onlygpt-mul-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-llama-onlygpt-mul-v1/tokenizer_config.json
rica40325-llama-onlygpt-mul-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-llama-onlygpt-mul-v1/tokenizer.json
rica40325-llama-onlygpt-mul-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-llama-onlygpt-mul-v1/flywheel_model.0.safetensors
rica40325-llama-onlygpt-mul-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:08, 33.93it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:04, 55.84it/s]
Loading 0:   7%|▋         | 19/291 [00:00<00:05, 48.35it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:05, 50.45it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:04, 53.21it/s]
Loading 0:  13%|█▎        | 37/291 [00:00<00:05, 48.85it/s]
Loading 0:  15%|█▍        | 43/291 [00:00<00:04, 50.52it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:04, 52.23it/s]
Loading 0:  19%|█▉        | 55/291 [00:01<00:04, 48.38it/s]
Loading 0:  21%|██        | 60/291 [00:01<00:04, 47.66it/s]
Loading 0:  23%|██▎       | 67/291 [00:01<00:04, 52.70it/s]
Loading 0:  25%|██▌       | 73/291 [00:01<00:04, 47.67it/s]
Loading 0:  27%|██▋       | 78/291 [00:01<00:04, 46.11it/s]
Loading 0:  29%|██▊       | 83/291 [00:01<00:05, 34.67it/s]
Loading 0:  30%|██▉       | 87/291 [00:01<00:05, 34.54it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:04, 41.71it/s]
Loading 0:  34%|███▍      | 100/291 [00:02<00:04, 41.56it/s]
Loading 0:  36%|███▌      | 105/291 [00:02<00:04, 42.67it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:03, 47.57it/s]
Loading 0:  41%|████      | 118/291 [00:02<00:03, 45.18it/s]
Loading 0:  42%|████▏     | 123/291 [00:02<00:03, 45.06it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:03, 49.94it/s]
Loading 0:  47%|████▋     | 136/291 [00:02<00:03, 46.08it/s]
Loading 0:  48%|████▊     | 141/291 [00:03<00:03, 45.46it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:02, 50.87it/s]
Loading 0:  53%|█████▎    | 154/291 [00:03<00:02, 46.45it/s]
Loading 0:  55%|█████▍    | 159/291 [00:03<00:02, 45.59it/s]
Loading 0:  57%|█████▋    | 166/291 [00:03<00:02, 50.16it/s]
Loading 0:  59%|█████▉    | 172/291 [00:03<00:02, 45.09it/s]
Loading 0:  61%|██████    | 177/291 [00:03<00:02, 45.72it/s]
Loading 0:  63%|██████▎   | 182/291 [00:03<00:02, 43.78it/s]
Loading 0:  64%|██████▍   | 187/291 [00:04<00:03, 33.62it/s]
Loading 0:  66%|██████▌   | 191/291 [00:04<00:02, 34.60it/s]
Loading 0:  67%|██████▋   | 195/291 [00:04<00:02, 32.62it/s]
Loading 0:  69%|██████▉   | 201/291 [00:04<00:02, 38.56it/s]
Loading 0:  71%|███████   | 206/291 [00:04<00:02, 40.11it/s]
Loading 0:  73%|███████▎  | 211/291 [00:04<00:01, 41.68it/s]
Loading 0:  75%|███████▍  | 217/291 [00:04<00:01, 40.11it/s]
Loading 0:  76%|███████▋  | 222/291 [00:05<00:01, 40.87it/s]
Loading 0:  78%|███████▊  | 228/291 [00:05<00:01, 45.14it/s]
Loading 0:  80%|████████  | 233/291 [00:05<00:01, 45.13it/s]
Loading 0:  82%|████████▏ | 238/291 [00:05<00:01, 45.30it/s]
Loading 0:  84%|████████▍ | 244/291 [00:05<00:01, 42.61it/s]
Loading 0:  86%|████████▌ | 249/291 [00:05<00:01, 41.94it/s]
Loading 0:  88%|████████▊ | 255/291 [00:05<00:00, 45.06it/s]
Loading 0:  89%|████████▉ | 260/291 [00:05<00:00, 44.96it/s]
Loading 0:  91%|█████████▏| 266/291 [00:06<00:00, 40.97it/s]
Loading 0:  94%|█████████▍| 274/291 [00:06<00:00, 48.48it/s]
Loading 0:  96%|█████████▌| 280/291 [00:06<00:00, 45.36it/s]
Loading 0:  98%|█████████▊| 285/291 [00:06<00:00, 44.77it/s]
Loading 0: 100%|█████████▉| 290/291 [00:11<00:00,  3.25it/s]
                                                            
Job rica40325-llama-onlygpt-mul-v1-mkmlizer completed after 73.78s with status: succeeded
Stopping job with name rica40325-llama-onlygpt-mul-v1-mkmlizer
Pipeline stage MKMLizer completed in 74.31s
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-llama-onlygpt-mul-v1
Waiting for inference service rica40325-llama-onlygpt-mul-v1 to be ready
Inference service rica40325-llama-onlygpt-mul-v1 ready after 140.53901076316833s
Pipeline stage MKMLDeployer completed in 141.39s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.790588617324829s
Received healthy response to inference request in 1.2628631591796875s
Received healthy response to inference request in 1.3723618984222412s
Received healthy response to inference request in 1.3814496994018555s
Received healthy response to inference request in 1.1397268772125244s
5 requests
0 failed requests
5th percentile: 1.164354133605957
10th percentile: 1.1889813899993897
20th percentile: 1.2382359027862548
30th percentile: 1.2847629070281983
40th percentile: 1.3285624027252196
50th percentile: 1.3723618984222412
60th percentile: 1.3759970188140869
70th percentile: 1.3796321392059325
80th percentile: 1.4632774829864503
90th percentile: 1.6269330501556396
95th percentile: 1.7087608337402342
99th percentile: 1.7742230606079101
mean time: 1.3893980503082275
Pipeline stage StressChecker completed in 8.38s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 0.86s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.74s
Shutdown handler de-registered
rica40325-llama-onlygpt-mul_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 2683.29s
Shutdown handler de-registered
rica40325-llama-onlygpt-mul_v1 status is now inactive due to auto deactivation removed underperforming models
rica40325-llama-onlygpt-mul_v1 status is now torndown due to DeploymentManager action