chaiml-gy-exp1-llama31-_61011

developer_uid: bogoconic1

submission_id: chaiml-gy-exp1-llama31-_61011_v1

model_name: chaiml-gy-exp1-llama31-_61011_v1

model_group: ChaiML/gy-exp1-llama31-8

status: torndown

timestamp: 2025-06-24T06:49:57+00:00

num_battles: 6305

num_wins: 2657

celo_rating: 1218.65

family_friendly_score: 0.6032

family_friendly_standard_error: 0.006918811458624956

submission_type: basic

model_repo: ChaiML/gy-exp1-llama31-8b-sft-full-332k-public-ep2

model_architecture: LlamaForCausalLM

model_num_parameters: 8030261248.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.8444088277651537, 'latency_mean': 1.1841540586948396, 'latency_p50': 1.1802564859390259, 'latency_p90': 1.3102766036987306}, {'batch_size': 4, 'throughput': 1.745965653154823, 'latency_mean': 2.2830718994140624, 'latency_p50': 2.2719451189041138, 'latency_p90': 2.5409621953964234}, {'batch_size': 5, 'throughput': 1.8640678803962247, 'latency_mean': 2.6667585456371308, 'latency_p50': 2.6846680641174316, 'latency_p90': 2.9697391510009767}, {'batch_size': 8, 'throughput': 2.0560255824181515, 'latency_mean': 3.866929029226303, 'latency_p50': 3.8704417943954468, 'latency_p90': 4.33974940776825}, {'batch_size': 10, 'throughput': 2.110652477249486, 'latency_mean': 4.691095957756042, 'latency_p50': 4.673622369766235, 'latency_p90': 5.316197443008423}, {'batch_size': 12, 'throughput': 2.151264713614267, 'latency_mean': 5.523635494709015, 'latency_p50': 5.493714690208435, 'latency_p90': 6.243496060371399}, {'batch_size': 15, 'throughput': 2.1749693925321933, 'latency_mean': 6.805572147369385, 'latency_p50': 6.816344499588013, 'latency_p90': 7.679996347427368}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-gy-exp1-llama31-_61011_v1

is_internal_developer: True

language_model: ChaiML/gy-exp1-llama31-8b-sft-full-332k-public-ep2

model_size: 8B

ranking_group: single

throughput_3p7s: 2.05

us_pacific_date: 2025-06-23

win_ratio: 0.42141157811260904

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 chaiml-gy-exp1-llama31-61011-v1-mkmlizer
Waiting for job on chaiml-gy-exp1-llama31-61011-v1-mkmlizer to finish
chaiml-gy-exp1-llama31-61011-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp1-llama31-61011-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp1-llama31-61011-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp1-llama31-61011-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp1-llama31-61011-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp1-llama31-61011-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp1-llama31-61011-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp1-llama31-61011-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp1-llama31-61011-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp1-llama31-61011-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp1-llama31-61011-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp1-llama31-61011-v1-mkmlizer: ║  Version: 0.29.3                                                    ║
chaiml-gy-exp1-llama31-61011-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp1-llama31-61011-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp1-llama31-61011-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp1-llama31-61011-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp1-llama31-61011-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp1-llama31-61011-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp1-llama31-61011-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp1-llama31-61011-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp1-llama31-61011-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp1-llama31-61011-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp1-llama31-61011-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp1-llama31-61011-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission chaiml-giyu-disabled-hu_13897_v2: ('http://chaiml-giyu-disabled-hu-13897-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
chaiml-gy-exp1-llama31-61011-v1-mkmlizer: Downloaded to shared memory in 30.749s
chaiml-gy-exp1-llama31-61011-v1-mkmlizer: Checking if ChaiML/gy-exp1-llama31-8b-sft-full-332k-public-ep2 already exists in ChaiML
chaiml-gy-exp1-llama31-61011-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmppt11jijy, device:0
chaiml-gy-exp1-llama31-61011-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp1-llama31-61011-v1-mkmlizer: quantized model in 22.077s
chaiml-gy-exp1-llama31-61011-v1-mkmlizer: Processed model ChaiML/gy-exp1-llama31-8b-sft-full-332k-public-ep2 in 52.827s
chaiml-gy-exp1-llama31-61011-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp1-llama31-61011-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp1-llama31-61011-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp1-llama31-61011-v1
chaiml-gy-exp1-llama31-61011-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp1-llama31-61011-v1/config.json
chaiml-gy-exp1-llama31-61011-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp1-llama31-61011-v1/special_tokens_map.json
chaiml-gy-exp1-llama31-61011-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp1-llama31-61011-v1/tokenizer_config.json
chaiml-gy-exp1-llama31-61011-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp1-llama31-61011-v1/tokenizer.json
chaiml-gy-exp1-llama31-61011-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp1-llama31-61011-v1/flywheel_model.0.safetensors
chaiml-gy-exp1-llama31-61011-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:08, 31.90it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:05, 49.71it/s]
Loading 0:   6%|▌         | 18/291 [00:00<00:05, 51.59it/s]
Loading 0:   8%|▊         | 24/291 [00:00<00:06, 41.44it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:05, 48.29it/s]
Loading 0:  13%|█▎        | 37/291 [00:00<00:05, 44.64it/s]
Loading 0:  14%|█▍        | 42/291 [00:00<00:05, 44.12it/s]
Loading 0:  17%|█▋        | 49/291 [00:01<00:04, 49.72it/s]
Loading 0:  19%|█▉        | 55/291 [00:01<00:05, 44.95it/s]
Loading 0:  21%|██        | 60/291 [00:01<00:05, 44.16it/s]
Loading 0:  23%|██▎       | 66/291 [00:01<00:04, 47.17it/s]
Loading 0:  24%|██▍       | 71/291 [00:01<00:04, 46.57it/s]
Loading 0:  26%|██▌       | 76/291 [00:01<00:04, 45.90it/s]
Loading 0:  28%|██▊       | 81/291 [00:01<00:04, 46.79it/s]
Loading 0:  30%|██▉       | 86/291 [00:02<00:08, 25.48it/s]
Loading 0:  32%|███▏      | 93/291 [00:02<00:06, 32.59it/s]
Loading 0:  34%|███▎      | 98/291 [00:02<00:05, 35.45it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:04, 38.16it/s]
Loading 0:  37%|███▋      | 109/291 [00:02<00:04, 38.13it/s]
Loading 0:  39%|███▉      | 114/291 [00:02<00:04, 39.44it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:03, 45.16it/s]
Loading 0:  44%|████▎     | 127/291 [00:03<00:03, 42.66it/s]
Loading 0:  45%|████▌     | 132/291 [00:03<00:03, 42.58it/s]
Loading 0:  48%|████▊     | 139/291 [00:03<00:03, 47.87it/s]
Loading 0:  49%|████▉     | 144/291 [00:03<00:03, 48.08it/s]
Loading 0:  51%|█████     | 149/291 [00:03<00:03, 40.05it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:02, 48.12it/s]
Loading 0:  56%|█████▌    | 163/291 [00:03<00:02, 44.55it/s]
Loading 0:  58%|█████▊    | 168/291 [00:03<00:02, 43.69it/s]
Loading 0:  60%|█████▉    | 174/291 [00:04<00:02, 47.48it/s]
Loading 0:  62%|██████▏   | 180/291 [00:04<00:02, 48.94it/s]
Loading 0:  64%|██████▍   | 186/291 [00:04<00:02, 44.82it/s]
Loading 0:  66%|██████▌   | 191/291 [00:04<00:03, 31.75it/s]
Loading 0:  67%|██████▋   | 195/291 [00:04<00:02, 32.17it/s]
Loading 0:  69%|██████▉   | 202/291 [00:04<00:02, 39.27it/s]
Loading 0:  71%|███████▏  | 208/291 [00:05<00:02, 39.02it/s]
Loading 0:  73%|███████▎  | 213/291 [00:05<00:01, 40.17it/s]
Loading 0:  76%|███████▌  | 220/291 [00:05<00:01, 45.73it/s]
Loading 0:  78%|███████▊  | 226/291 [00:05<00:01, 43.25it/s]
Loading 0:  79%|███████▉  | 231/291 [00:05<00:01, 43.10it/s]
Loading 0:  81%|████████▏ | 237/291 [00:05<00:01, 46.98it/s]
Loading 0:  83%|████████▎ | 242/291 [00:05<00:01, 47.10it/s]
Loading 0:  85%|████████▍ | 247/291 [00:05<00:00, 47.54it/s]
Loading 0:  87%|████████▋ | 253/291 [00:05<00:00, 44.37it/s]
Loading 0:  89%|████████▊ | 258/291 [00:06<00:00, 43.79it/s]
Loading 0:  91%|█████████ | 265/291 [00:06<00:00, 49.46it/s]
Loading 0:  93%|█████████▎| 271/291 [00:06<00:00, 46.25it/s]
Loading 0:  95%|█████████▍| 276/291 [00:06<00:00, 45.59it/s]
Loading 0:  97%|█████████▋| 282/291 [00:06<00:00, 40.06it/s]
Loading 0:  99%|█████████▊| 287/291 [00:07<00:00, 25.20it/s]
                                                            
Job chaiml-gy-exp1-llama31-61011-v1-mkmlizer completed after 74.19s with status: succeeded
Stopping job with name chaiml-gy-exp1-llama31-61011-v1-mkmlizer
Pipeline stage MKMLizer completed in 74.83s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-gy-exp1-llama31-61011-v1
Waiting for inference service chaiml-gy-exp1-llama31-61011-v1 to be ready
Inference service chaiml-gy-exp1-llama31-61011-v1 ready after 131.16765975952148s
Pipeline stage MKMLDeployer completed in 131.89s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1444473266601562s
Received healthy response to inference request in 1.3639805316925049s
Received healthy response to inference request in 1.5377936363220215s
Received healthy response to inference request in 1.2477941513061523s
Received healthy response to inference request in 1.3212690353393555s
5 requests
0 failed requests
5th percentile: 1.262489128112793
10th percentile: 1.2771841049194337
20th percentile: 1.3065740585327148
30th percentile: 1.3298113346099854
40th percentile: 1.3468959331512451
50th percentile: 1.3639805316925049
60th percentile: 1.4335057735443115
70th percentile: 1.5030310153961182
80th percentile: 1.6591243743896484
90th percentile: 1.9017858505249023
95th percentile: 2.0231165885925293
99th percentile: 2.120181179046631
mean time: 1.523056936264038
Pipeline stage StressChecker completed in 9.26s
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 0.71s
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 0.62s
Shutdown handler de-registered
chaiml-gy-exp1-llama31-_61011_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 2948.18s
Shutdown handler de-registered
chaiml-gy-exp1-llama31-_61011_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp1-llama31-_61011_v1 status is now torndown due to DeploymentManager action