developer_uid: huohuo12
submission_id: yamatazen-ayla-light-12b-v2_v5
model_name: yamatazen-ayla-light-12b-v2_v2
model_group: yamatazen/Ayla-Light-12B
status: torndown
timestamp: 2025-02-26T09:34:14+00:00
num_battles: 5341
num_wins: 2599
celo_rating: 1256.98
family_friendly_score: 0.5614
family_friendly_standard_error: 0.007017549999821875
submission_type: basic
model_repo: yamatazen/Ayla-Light-12B-v2
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.5945836455666496, 'latency_mean': 1.6817562615871429, 'latency_p50': 1.670311689376831, 'latency_p90': 1.862287139892578}, {'batch_size': 3, 'throughput': 1.0770347960239646, 'latency_mean': 2.7775958037376403, 'latency_p50': 2.7715299129486084, 'latency_p90': 3.0551671028137206}, {'batch_size': 5, 'throughput': 1.2985569747908343, 'latency_mean': 3.8316058886051176, 'latency_p50': 3.816219925880432, 'latency_p90': 4.279991865158081}, {'batch_size': 6, 'throughput': 1.370755935832761, 'latency_mean': 4.358708597421646, 'latency_p50': 4.330424189567566, 'latency_p90': 4.944117617607117}, {'batch_size': 8, 'throughput': 1.4268138164118511, 'latency_mean': 5.568418595790863, 'latency_p50': 5.54000449180603, 'latency_p90': 6.269010257720947}, {'batch_size': 10, 'throughput': 1.4500261962437646, 'latency_mean': 6.853660222291946, 'latency_p50': 6.928355574607849, 'latency_p90': 7.712348294258118}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: yamatazen-ayla-light-12b-v2_v2
is_internal_developer: False
language_model: yamatazen/Ayla-Light-12B-v2
model_size: 13B
ranking_group: single
throughput_3p7s: 1.28
us_pacific_date: 2025-02-26
win_ratio: 0.4866129938213818
generation_params: {'temperature': 0.95, 'top_p': 0.87, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.2, 'frequency_penalty': 0.3, '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 yamatazen-ayla-light-12b-v2-v5-mkmlizer
Waiting for job on yamatazen-ayla-light-12b-v2-v5-mkmlizer to finish
yamatazen-ayla-light-12b-v2-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
yamatazen-ayla-light-12b-v2-v5-mkmlizer: ║ _____ __ __ ║
yamatazen-ayla-light-12b-v2-v5-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
yamatazen-ayla-light-12b-v2-v5-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
yamatazen-ayla-light-12b-v2-v5-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
yamatazen-ayla-light-12b-v2-v5-mkmlizer: ║ /___/ ║
yamatazen-ayla-light-12b-v2-v5-mkmlizer: ║ ║
yamatazen-ayla-light-12b-v2-v5-mkmlizer: ║ Version: 0.12.8 ║
yamatazen-ayla-light-12b-v2-v5-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
yamatazen-ayla-light-12b-v2-v5-mkmlizer: ║ https://mk1.ai ║
yamatazen-ayla-light-12b-v2-v5-mkmlizer: ║ ║
yamatazen-ayla-light-12b-v2-v5-mkmlizer: ║ The license key for the current software has been verified as ║
yamatazen-ayla-light-12b-v2-v5-mkmlizer: ║ belonging to: ║
yamatazen-ayla-light-12b-v2-v5-mkmlizer: ║ ║
yamatazen-ayla-light-12b-v2-v5-mkmlizer: ║ Chai Research Corp. ║
yamatazen-ayla-light-12b-v2-v5-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
yamatazen-ayla-light-12b-v2-v5-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
yamatazen-ayla-light-12b-v2-v5-mkmlizer: ║ ║
yamatazen-ayla-light-12b-v2-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission nischaydnk-exp16-mistra_31861_v2: HTTPConnectionPool(host='nischaydnk-exp16-mistra-31861-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission nischaydnk-exp16-mistra_31861_v2: HTTPConnectionPool(host='nischaydnk-exp16-mistra-31861-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
yamatazen-ayla-light-12b-v2-v5-mkmlizer: Downloaded to shared memory in 34.534s
yamatazen-ayla-light-12b-v2-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpmruo_u5q, device:0
yamatazen-ayla-light-12b-v2-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
yamatazen-ayla-light-12b-v2-v5-mkmlizer: quantized model in 35.228s
yamatazen-ayla-light-12b-v2-v5-mkmlizer: Processed model yamatazen/Ayla-Light-12B-v2 in 69.763s
yamatazen-ayla-light-12b-v2-v5-mkmlizer: creating bucket guanaco-mkml-models
yamatazen-ayla-light-12b-v2-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
yamatazen-ayla-light-12b-v2-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/yamatazen-ayla-light-12b-v2-v5
yamatazen-ayla-light-12b-v2-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/yamatazen-ayla-light-12b-v2-v5/config.json
yamatazen-ayla-light-12b-v2-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/yamatazen-ayla-light-12b-v2-v5/special_tokens_map.json
yamatazen-ayla-light-12b-v2-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/yamatazen-ayla-light-12b-v2-v5/tokenizer_config.json
yamatazen-ayla-light-12b-v2-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/yamatazen-ayla-light-12b-v2-v5/tokenizer.json
yamatazen-ayla-light-12b-v2-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/yamatazen-ayla-light-12b-v2-v5/flywheel_model.0.safetensors
yamatazen-ayla-light-12b-v2-v5-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 2/363 [00:06<18:16, 3.04s/it] Loading 0: 2%|▏ | 6/363 [00:06<04:52, 1.22it/s] Loading 0: 3%|▎ | 11/363 [00:06<02:08, 2.75it/s] Loading 0: 4%|▍ | 15/363 [00:06<01:20, 4.32it/s] Loading 0: 6%|▋ | 23/363 [00:06<00:39, 8.66it/s] Loading 0: 8%|▊ | 29/363 [00:06<00:27, 12.28it/s] Loading 0: 9%|▉ | 34/363 [00:06<00:20, 15.70it/s] Loading 0: 11%|█ | 40/363 [00:07<00:17, 18.02it/s] Loading 0: 12%|█▏ | 45/363 [00:07<00:14, 21.60it/s] Loading 0: 14%|█▍ | 50/363 [00:07<00:12, 25.83it/s] Loading 0: 15%|█▌ | 56/363 [00:07<00:10, 29.45it/s] Loading 0: 17%|█▋ | 61/363 [00:07<00:09, 32.34it/s] Loading 0: 19%|█▊ | 68/363 [00:07<00:07, 39.58it/s] Loading 0: 20%|██ | 74/363 [00:07<00:07, 40.89it/s] Loading 0: 22%|██▏ | 79/363 [00:07<00:06, 42.04it/s] Loading 0: 24%|██▎ | 86/363 [00:07<00:05, 47.78it/s] Loading 0: 25%|██▌ | 92/363 [00:08<00:05, 46.38it/s] Loading 0: 27%|██▋ | 97/363 [00:08<00:05, 46.42it/s] Loading 0: 29%|██▊ | 104/363 [00:08<00:05, 50.69it/s] Loading 0: 30%|███ | 110/363 [00:08<00:05, 49.00it/s] Loading 0: 32%|███▏ | 116/363 [00:08<00:04, 49.69it/s] Loading 0: 34%|███▎ | 122/363 [00:08<00:06, 38.30it/s] Loading 0: 35%|███▍ | 127/363 [00:08<00:05, 40.77it/s] Loading 0: 36%|███▋ | 132/363 [00:09<00:06, 37.56it/s] Loading 0: 39%|███▊ | 140/363 [00:09<00:04, 46.03it/s] Loading 0: 40%|████ | 146/363 [00:09<00:04, 45.71it/s] Loading 0: 42%|████▏ | 151/363 [00:09<00:04, 44.71it/s] Loading 0: 44%|████▎ | 158/363 [00:09<00:04, 49.63it/s] Loading 0: 45%|████▌ | 164/363 [00:09<00:04, 48.21it/s] Loading 0: 47%|████▋ | 169/363 [00:09<00:04, 47.16it/s] Loading 0: 48%|████▊ | 175/363 [00:09<00:03, 50.32it/s] Loading 0: 50%|████▉ | 181/363 [00:10<00:03, 52.12it/s] Loading 0: 52%|█████▏ | 187/363 [00:10<00:04, 43.67it/s] Loading 0: 53%|█████▎ | 193/363 [00:10<00:03, 46.21it/s] Loading 0: 55%|█████▍ | 198/363 [00:10<00:03, 45.15it/s] Loading 0: 56%|█████▌ | 203/363 [00:10<00:04, 33.94it/s] Loading 0: 57%|█████▋ | 207/363 [00:10<00:04, 33.15it/s] Loading 0: 58%|█████▊ | 212/363 [00:10<00:04, 36.03it/s] Loading 0: 60%|██████ | 218/363 [00:11<00:03, 38.08it/s] Loading 0: 61%|██████▏ | 223/363 [00:11<00:03, 37.92it/s] Loading 0: 63%|██████▎ | 230/363 [00:11<00:02, 44.39it/s] Loading 0: 65%|██████▌ | 236/363 [00:11<00:02, 43.25it/s] Loading 0: 66%|██████▋ | 241/363 [00:11<00:02, 42.54it/s] Loading 0: 68%|██████▊ | 248/363 [00:11<00:02, 47.58it/s] Loading 0: 70%|██████▉ | 254/363 [00:11<00:02, 44.99it/s] Loading 0: 71%|███████▏ | 259/363 [00:11<00:02, 44.00it/s] Loading 0: 73%|███████▎ | 266/363 [00:12<00:01, 48.61it/s] Loading 0: 75%|███████▍ | 272/363 [00:12<00:01, 46.49it/s] Loading 0: 76%|███████▋ | 277/363 [00:12<00:01, 44.29it/s] Loading 0: 78%|███████▊ | 283/363 [00:12<00:02, 35.82it/s] Loading 0: 79%|███████▉ | 287/363 [00:12<00:02, 35.87it/s] Loading 0: 81%|████████ | 293/363 [00:12<00:01, 39.83it/s] Loading 0: 82%|████████▏ | 298/363 [00:12<00:01, 42.07it/s] Loading 0: 83%|████████▎ | 303/363 [00:13<00:01, 36.67it/s] Loading 0: 85%|████████▌ | 310/363 [00:13<00:01, 43.95it/s] Loading 0: 87%|████████▋ | 315/363 [00:13<00:01, 42.50it/s] Loading 0: 88%|████████▊ | 320/363 [00:13<00:00, 43.19it/s] Loading 0: 90%|████████▉ | 326/363 [00:13<00:00, 43.08it/s] Loading 0: 91%|█████████ | 331/363 [00:13<00:00, 43.34it/s] Loading 0: 93%|█████████▎| 337/363 [00:13<00:00, 46.63it/s] Loading 0: 94%|█████████▍| 342/363 [00:13<00:00, 44.35it/s] Loading 0: 96%|█████████▌| 347/363 [00:14<00:00, 45.00it/s] Loading 0: 97%|█████████▋| 353/363 [00:14<00:00, 44.47it/s] Loading 0: 99%|█████████▊| 358/363 [00:14<00:00, 43.71it/s]
Job yamatazen-ayla-light-12b-v2-v5-mkmlizer completed after 94.14s with status: succeeded
Stopping job with name yamatazen-ayla-light-12b-v2-v5-mkmlizer
Pipeline stage MKMLizer completed in 94.66s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service yamatazen-ayla-light-12b-v2-v5
Waiting for inference service yamatazen-ayla-light-12b-v2-v5 to be ready
Inference service yamatazen-ayla-light-12b-v2-v5 ready after 270.9984452724457s
Pipeline stage MKMLDeployer completed in 271.56s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1688072681427s
Received healthy response to inference request in 1.4407196044921875s
Received healthy response to inference request in 1.5301849842071533s
Received healthy response to inference request in 1.5768327713012695s
Received healthy response to inference request in 1.5413811206817627s
5 requests
0 failed requests
5th percentile: 1.4586126804351807
10th percentile: 1.4765057563781738
20th percentile: 1.5122919082641602
30th percentile: 1.5324242115020752
40th percentile: 1.536902666091919
50th percentile: 1.5413811206817627
60th percentile: 1.5555617809295654
70th percentile: 1.5697424411773682
80th percentile: 1.6952276706695557
90th percentile: 1.932017469406128
95th percentile: 2.050412368774414
99th percentile: 2.145128288269043
mean time: 1.6515851497650147
Pipeline stage StressChecker completed in 9.40s
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 0.65s
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 0.58s
Shutdown handler de-registered
yamatazen-ayla-light-12b-v2_v5 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 2616.40s
Shutdown handler de-registered
yamatazen-ayla-light-12b-v2_v5 status is now inactive due to auto deactivation removed underperforming models
yamatazen-ayla-light-12b-v2_v5 status is now torndown due to DeploymentManager action