developer_uid: huohuo12
submission_id: yamatazen-ayla-light-12b-v2_v9
model_name: yamatazen-ayla-light-12b-v2_v2
model_group: yamatazen/Ayla-Light-12B
status: torndown
timestamp: 2025-02-26T09:41:28+00:00
num_battles: 5533
num_wins: 2780
celo_rating: 1268.16
family_friendly_score: 0.5609999999999999
family_friendly_standard_error: 0.007018247644533499
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': 0.6015387788442136, 'latency_mean': 1.6623414325714112, 'latency_p50': 1.6563208103179932, 'latency_p90': 1.8451622247695922}, {'batch_size': 3, 'throughput': 1.0734213570594298, 'latency_mean': 2.7849606394767763, 'latency_p50': 2.789351463317871, 'latency_p90': 3.0418226957321166}, {'batch_size': 5, 'throughput': 1.3012661812328672, 'latency_mean': 3.820153924226761, 'latency_p50': 3.8187713623046875, 'latency_p90': 4.266002464294433}, {'batch_size': 6, 'throughput': 1.3581607788277046, 'latency_mean': 4.4002481150627135, 'latency_p50': 4.414311051368713, 'latency_p90': 4.930312657356263}, {'batch_size': 8, 'throughput': 1.4184977829250491, 'latency_mean': 5.595264890193939, 'latency_p50': 5.613605499267578, 'latency_p90': 6.25406014919281}, {'batch_size': 10, 'throughput': 1.4573291652918114, 'latency_mean': 6.812791746854782, 'latency_p50': 6.813913702964783, 'latency_p90': 7.652965974807739}]
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: 1.29
us_pacific_date: 2025-02-26
win_ratio: 0.5024399060184348
generation_params: {'temperature': 0.96, 'top_p': 0.83, 'min_p': 0.12, 'top_k': 58, 'presence_penalty': 0.3, '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-v9-mkmlizer
Waiting for job on yamatazen-ayla-light-12b-v2-v9-mkmlizer to finish
yamatazen-ayla-light-12b-v2-v9-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
yamatazen-ayla-light-12b-v2-v9-mkmlizer: ║ _____ __ __ ║
yamatazen-ayla-light-12b-v2-v9-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
yamatazen-ayla-light-12b-v2-v9-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
yamatazen-ayla-light-12b-v2-v9-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
yamatazen-ayla-light-12b-v2-v9-mkmlizer: ║ /___/ ║
yamatazen-ayla-light-12b-v2-v9-mkmlizer: ║ ║
yamatazen-ayla-light-12b-v2-v9-mkmlizer: ║ Version: 0.12.8 ║
yamatazen-ayla-light-12b-v2-v9-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
yamatazen-ayla-light-12b-v2-v9-mkmlizer: ║ https://mk1.ai ║
yamatazen-ayla-light-12b-v2-v9-mkmlizer: ║ ║
yamatazen-ayla-light-12b-v2-v9-mkmlizer: ║ The license key for the current software has been verified as ║
yamatazen-ayla-light-12b-v2-v9-mkmlizer: ║ belonging to: ║
yamatazen-ayla-light-12b-v2-v9-mkmlizer: ║ ║
yamatazen-ayla-light-12b-v2-v9-mkmlizer: ║ Chai Research Corp. ║
yamatazen-ayla-light-12b-v2-v9-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
yamatazen-ayla-light-12b-v2-v9-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
yamatazen-ayla-light-12b-v2-v9-mkmlizer: ║ ║
yamatazen-ayla-light-12b-v2-v9-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)
yamatazen-ayla-light-12b-v2-v9-mkmlizer: Downloaded to shared memory in 31.556s
yamatazen-ayla-light-12b-v2-v9-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpsstat5z3, device:0
yamatazen-ayla-light-12b-v2-v9-mkmlizer: Saving flywheel model at /dev/shm/model_cache
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-v9-mkmlizer: quantized model in 35.382s
yamatazen-ayla-light-12b-v2-v9-mkmlizer: Processed model yamatazen/Ayla-Light-12B-v2 in 66.938s
yamatazen-ayla-light-12b-v2-v9-mkmlizer: creating bucket guanaco-mkml-models
yamatazen-ayla-light-12b-v2-v9-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
yamatazen-ayla-light-12b-v2-v9-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/yamatazen-ayla-light-12b-v2-v9
yamatazen-ayla-light-12b-v2-v9-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/yamatazen-ayla-light-12b-v2-v9/config.json
yamatazen-ayla-light-12b-v2-v9-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/yamatazen-ayla-light-12b-v2-v9/special_tokens_map.json
yamatazen-ayla-light-12b-v2-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/yamatazen-ayla-light-12b-v2-v9/tokenizer_config.json
yamatazen-ayla-light-12b-v2-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/yamatazen-ayla-light-12b-v2-v9/tokenizer.json
yamatazen-ayla-light-12b-v2-v9-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/yamatazen-ayla-light-12b-v2-v9/flywheel_model.0.safetensors
yamatazen-ayla-light-12b-v2-v9-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 2/363 [00:06<18:19, 3.05s/it] Loading 0: 2%|▏ | 6/363 [00:06<04:52, 1.22it/s] Loading 0: 4%|▎ | 13/363 [00:06<01:43, 3.37it/s] Loading 0: 6%|▌ | 20/363 [00:06<00:56, 6.10it/s] Loading 0: 7%|▋ | 25/363 [00:06<00:40, 8.43it/s] Loading 0: 9%|▉ | 32/363 [00:06<00:25, 12.81it/s] Loading 0: 10%|█ | 37/363 [00:06<00:20, 16.15it/s] Loading 0: 12%|█▏ | 42/363 [00:07<00:20, 16.01it/s] Loading 0: 14%|█▍ | 50/363 [00:07<00:13, 23.21it/s] Loading 0: 15%|█▌ | 56/363 [00:07<00:11, 26.87it/s] Loading 0: 17%|█▋ | 61/363 [00:07<00:10, 30.19it/s] Loading 0: 19%|█▊ | 68/363 [00:07<00:07, 37.06it/s] Loading 0: 20%|██ | 74/363 [00:07<00:07, 39.04it/s] Loading 0: 22%|██▏ | 79/363 [00:07<00:07, 40.32it/s] Loading 0: 24%|██▎ | 86/363 [00:07<00:05, 46.34it/s] Loading 0: 25%|██▌ | 92/363 [00:08<00:06, 43.91it/s] Loading 0: 27%|██▋ | 97/363 [00:08<00:06, 43.65it/s] Loading 0: 29%|██▊ | 104/363 [00:08<00:05, 48.52it/s] Loading 0: 30%|███ | 110/363 [00:08<00:05, 45.90it/s] Loading 0: 32%|███▏ | 115/363 [00:08<00:05, 45.26it/s] Loading 0: 33%|███▎ | 121/363 [00:08<00:06, 35.57it/s] Loading 0: 34%|███▍ | 125/363 [00:09<00:06, 35.66it/s] Loading 0: 36%|███▌ | 130/363 [00:09<00:06, 38.60it/s] Loading 0: 37%|███▋ | 135/363 [00:09<00:05, 39.20it/s] Loading 0: 39%|███▊ | 140/363 [00:09<00:05, 41.28it/s] Loading 0: 40%|████ | 146/363 [00:09<00:05, 41.77it/s] Loading 0: 42%|████▏ | 151/363 [00:09<00:05, 41.93it/s] Loading 0: 44%|████▎ | 158/363 [00:09<00:04, 47.35it/s] Loading 0: 45%|████▍ | 163/363 [00:09<00:04, 47.09it/s] Loading 0: 46%|████▋ | 168/363 [00:09<00:04, 40.44it/s] Loading 0: 48%|████▊ | 176/363 [00:10<00:03, 47.89it/s] Loading 0: 50%|█████ | 182/363 [00:10<00:03, 47.14it/s] Loading 0: 52%|█████▏ | 187/363 [00:10<00:03, 46.44it/s] Loading 0: 53%|█████▎ | 194/363 [00:10<00:03, 50.00it/s] Loading 0: 55%|█████▌ | 200/363 [00:10<00:03, 46.29it/s] Loading 0: 56%|█████▋ | 205/363 [00:10<00:04, 34.50it/s] Loading 0: 58%|█████▊ | 212/363 [00:10<00:03, 40.15it/s] Loading 0: 60%|██████ | 218/363 [00:11<00:03, 40.09it/s] Loading 0: 61%|██████▏ | 223/363 [00:11<00:03, 40.43it/s] Loading 0: 63%|██████▎ | 230/363 [00:11<00:02, 46.22it/s] Loading 0: 65%|██████▌ | 236/363 [00:11<00:02, 43.58it/s] Loading 0: 66%|██████▋ | 241/363 [00:11<00:02, 43.27it/s] Loading 0: 68%|██████▊ | 248/363 [00:11<00:02, 47.99it/s] Loading 0: 70%|██████▉ | 253/363 [00:11<00:02, 46.07it/s] Loading 0: 71%|███████ | 258/363 [00:12<00:02, 38.70it/s] Loading 0: 73%|███████▎ | 266/363 [00:12<00:02, 47.07it/s] Loading 0: 75%|███████▍ | 272/363 [00:12<00:01, 45.66it/s] Loading 0: 76%|███████▋ | 277/363 [00:12<00:02, 42.28it/s] Loading 0: 78%|███████▊ | 283/363 [00:12<00:02, 33.51it/s] Loading 0: 79%|███████▉ | 287/363 [00:12<00:02, 33.09it/s] Loading 0: 80%|████████ | 292/363 [00:12<00:02, 35.07it/s] Loading 0: 82%|████████▏ | 296/363 [00:13<00:01, 34.98it/s] Loading 0: 83%|████████▎ | 302/363 [00:13<00:01, 39.21it/s] Loading 0: 85%|████████▍ | 308/363 [00:13<00:01, 38.99it/s] Loading 0: 86%|████████▌ | 313/363 [00:13<00:01, 38.60it/s] Loading 0: 88%|████████▊ | 319/363 [00:13<00:01, 43.15it/s] Loading 0: 89%|████████▉ | 324/363 [00:13<00:00, 43.81it/s] Loading 0: 91%|█████████ | 329/363 [00:13<00:00, 43.96it/s] Loading 0: 92%|█████████▏| 335/363 [00:13<00:00, 42.69it/s] Loading 0: 94%|█████████▎| 340/363 [00:14<00:00, 40.64it/s] Loading 0: 96%|█████████▌| 347/363 [00:14<00:00, 46.26it/s] Loading 0: 97%|█████████▋| 353/363 [00:14<00:00, 45.08it/s] Loading 0: 99%|█████████▊| 358/363 [00:14<00:00, 44.94it/s]
Job yamatazen-ayla-light-12b-v2-v9-mkmlizer completed after 94.1s with status: succeeded
Stopping job with name yamatazen-ayla-light-12b-v2-v9-mkmlizer
Pipeline stage MKMLizer completed in 94.59s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service yamatazen-ayla-light-12b-v2-v9
Waiting for inference service yamatazen-ayla-light-12b-v2-v9 to be ready
Inference service yamatazen-ayla-light-12b-v2-v9 ready after 271.38440322875977s
Pipeline stage MKMLDeployer completed in 271.92s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.280449151992798s
Received healthy response to inference request in 1.4383118152618408s
Received healthy response to inference request in 1.4796421527862549s
Received healthy response to inference request in 1.583712100982666s
Received healthy response to inference request in 1.4459590911865234s
5 requests
0 failed requests
5th percentile: 1.4398412704467773
10th percentile: 1.4413707256317139
20th percentile: 1.444429636001587
30th percentile: 1.4526957035064698
40th percentile: 1.4661689281463623
50th percentile: 1.4796421527862549
60th percentile: 1.5212701320648194
70th percentile: 1.5628981113433837
80th percentile: 1.7230595111846925
90th percentile: 2.001754331588745
95th percentile: 2.1411017417907714
99th percentile: 2.2525796699523926
mean time: 1.6456148624420166
Pipeline stage StressChecker completed in 9.34s
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 0.57s
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 0.67s
Shutdown handler de-registered
yamatazen-ayla-light-12b-v2_v9 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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service yamatazen-ayla-light-12b-v2-v9-profiler
Waiting for inference service yamatazen-ayla-light-12b-v2-v9-profiler to be ready
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 2548.88s
Shutdown handler de-registered
yamatazen-ayla-light-12b-v2_v9 status is now inactive due to auto deactivation removed underperforming models
yamatazen-ayla-light-12b-v2_v9 status is now torndown due to DeploymentManager action