developer_uid: huohuo12
submission_id: yamatazen-ayla-light-12b-v2_v3
model_name: yamatazen-ayla-light-12b-v2_v2
model_group: yamatazen/Ayla-Light-12B
status: torndown
timestamp: 2025-02-26T09:09:48+00:00
num_battles: 5951
num_wins: 2816
celo_rating: 1249.66
family_friendly_score: 0.5634
family_friendly_standard_error: 0.007013992301107837
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
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.6010417725030688, 'latency_mean': 1.663682245016098, 'latency_p50': 1.6626231670379639, 'latency_p90': 1.8233983993530274}, {'batch_size': 3, 'throughput': 1.09980369730219, 'latency_mean': 2.7225512731075288, 'latency_p50': 2.7109910249710083, 'latency_p90': 3.0565373420715334}, {'batch_size': 5, 'throughput': 1.3347461544630148, 'latency_mean': 3.728919565677643, 'latency_p50': 3.7217246294021606, 'latency_p90': 4.157240486145019}, {'batch_size': 6, 'throughput': 1.3962150514528706, 'latency_mean': 4.285797792673111, 'latency_p50': 4.33906888961792, 'latency_p90': 4.747497987747193}, {'batch_size': 8, 'throughput': 1.469941747353692, 'latency_mean': 5.410530984401703, 'latency_p50': 5.456712603569031, 'latency_p90': 6.051920700073242}, {'batch_size': 10, 'throughput': 1.5010868947803957, 'latency_mean': 6.605144361257553, 'latency_p50': 6.585608601570129, 'latency_p90': 7.459426999092102}]
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: 1.34
us_pacific_date: 2025-02-26
win_ratio: 0.4731977818853974
generation_params: {'temperature': 1.15, '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-v3-mkmlizer
Waiting for job on yamatazen-ayla-light-12b-v2-v3-mkmlizer to finish
yamatazen-ayla-light-12b-v2-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
yamatazen-ayla-light-12b-v2-v3-mkmlizer: ║ _____ __ __ ║
yamatazen-ayla-light-12b-v2-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
yamatazen-ayla-light-12b-v2-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
yamatazen-ayla-light-12b-v2-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
yamatazen-ayla-light-12b-v2-v3-mkmlizer: ║ /___/ ║
yamatazen-ayla-light-12b-v2-v3-mkmlizer: ║ ║
yamatazen-ayla-light-12b-v2-v3-mkmlizer: ║ Version: 0.12.8 ║
yamatazen-ayla-light-12b-v2-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
yamatazen-ayla-light-12b-v2-v3-mkmlizer: ║ https://mk1.ai ║
yamatazen-ayla-light-12b-v2-v3-mkmlizer: ║ ║
yamatazen-ayla-light-12b-v2-v3-mkmlizer: ║ The license key for the current software has been verified as ║
yamatazen-ayla-light-12b-v2-v3-mkmlizer: ║ belonging to: ║
yamatazen-ayla-light-12b-v2-v3-mkmlizer: ║ ║
yamatazen-ayla-light-12b-v2-v3-mkmlizer: ║ Chai Research Corp. ║
yamatazen-ayla-light-12b-v2-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
yamatazen-ayla-light-12b-v2-v3-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
yamatazen-ayla-light-12b-v2-v3-mkmlizer: ║ ║
yamatazen-ayla-light-12b-v2-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
yamatazen-ayla-light-12b-v2-v3-mkmlizer: Downloaded to shared memory in 36.037s
yamatazen-ayla-light-12b-v2-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpbfu0acue, device:0
yamatazen-ayla-light-12b-v2-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
yamatazen-ayla-light-12b-v2-v3-mkmlizer: quantized model in 35.536s
yamatazen-ayla-light-12b-v2-v3-mkmlizer: Processed model yamatazen/Ayla-Light-12B-v2 in 71.574s
yamatazen-ayla-light-12b-v2-v3-mkmlizer: creating bucket guanaco-mkml-models
yamatazen-ayla-light-12b-v2-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
yamatazen-ayla-light-12b-v2-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/yamatazen-ayla-light-12b-v2-v3
yamatazen-ayla-light-12b-v2-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/yamatazen-ayla-light-12b-v2-v3/config.json
yamatazen-ayla-light-12b-v2-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/yamatazen-ayla-light-12b-v2-v3/special_tokens_map.json
yamatazen-ayla-light-12b-v2-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/yamatazen-ayla-light-12b-v2-v3/tokenizer_config.json
yamatazen-ayla-light-12b-v2-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/yamatazen-ayla-light-12b-v2-v3/tokenizer.json
yamatazen-ayla-light-12b-v2-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/yamatazen-ayla-light-12b-v2-v3/flywheel_model.0.safetensors
yamatazen-ayla-light-12b-v2-v3-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 2/363 [00:06<18:18, 3.04s/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: 5%|▌ | 19/363 [00:06<00:59, 5.78it/s] Loading 0: 7%|▋ | 24/363 [00:06<00:42, 8.06it/s] Loading 0: 9%|▉ | 32/363 [00:06<00:24, 13.27it/s] Loading 0: 10%|█ | 38/363 [00:06<00:19, 17.04it/s] Loading 0: 12%|█▏ | 43/363 [00:07<00:18, 17.27it/s] Loading 0: 14%|█▍ | 50/363 [00:07<00:13, 23.12it/s] Loading 0: 15%|█▌ | 56/363 [00:07<00:11, 26.70it/s] Loading 0: 17%|█▋ | 61/363 [00:07<00:10, 29.66it/s] Loading 0: 19%|█▊ | 68/363 [00:07<00:08, 36.42it/s] Loading 0: 20%|██ | 74/363 [00:07<00:07, 38.23it/s] Loading 0: 22%|██▏ | 79/363 [00:07<00:07, 39.51it/s] Loading 0: 24%|██▎ | 86/363 [00:07<00:06, 45.64it/s] Loading 0: 25%|██▌ | 92/363 [00:08<00:06, 45.11it/s] Loading 0: 27%|██▋ | 97/363 [00:08<00:05, 44.79it/s] Loading 0: 29%|██▊ | 104/363 [00:08<00:05, 48.79it/s] Loading 0: 30%|███ | 110/363 [00:08<00:05, 47.03it/s] Loading 0: 32%|███▏ | 115/363 [00:08<00:05, 45.64it/s] Loading 0: 33%|███▎ | 121/363 [00:08<00:06, 35.92it/s] Loading 0: 35%|███▍ | 126/363 [00:08<00:06, 37.23it/s] Loading 0: 36%|███▌ | 131/363 [00:09<00:05, 39.50it/s] Loading 0: 38%|███▊ | 137/363 [00:09<00:05, 40.05it/s] Loading 0: 39%|███▉ | 142/363 [00:09<00:05, 38.85it/s] Loading 0: 41%|████ | 148/363 [00:09<00:04, 43.39it/s] Loading 0: 42%|████▏ | 153/363 [00:09<00:04, 43.47it/s] Loading 0: 44%|████▎ | 158/363 [00:09<00:04, 44.51it/s] Loading 0: 45%|████▍ | 163/363 [00:09<00:04, 45.73it/s] Loading 0: 46%|████▋ | 168/363 [00:10<00:05, 36.87it/s] Loading 0: 48%|████▊ | 175/363 [00:10<00:04, 43.00it/s] Loading 0: 50%|████▉ | 180/363 [00:10<00:04, 44.28it/s] Loading 0: 51%|█████ | 185/363 [00:10<00:03, 44.51it/s] Loading 0: 53%|█████▎ | 191/363 [00:10<00:03, 43.80it/s] Loading 0: 54%|█████▍ | 196/363 [00:10<00:03, 43.37it/s] Loading 0: 56%|█████▌ | 202/363 [00:10<00:04, 33.94it/s] Loading 0: 57%|█████▋ | 206/363 [00:10<00:04, 33.87it/s] Loading 0: 58%|█████▊ | 212/363 [00:11<00:03, 38.47it/s] Loading 0: 60%|██████ | 218/363 [00:11<00:03, 39.31it/s] Loading 0: 61%|██████▏ | 223/363 [00:11<00:03, 39.63it/s] Loading 0: 63%|██████▎ | 230/363 [00:11<00:02, 44.65it/s] Loading 0: 65%|██████▌ | 236/363 [00:11<00:02, 44.40it/s] Loading 0: 66%|██████▋ | 241/363 [00:11<00:02, 44.00it/s] Loading 0: 68%|██████▊ | 248/363 [00:11<00:02, 47.89it/s] Loading 0: 70%|██████▉ | 254/363 [00:11<00:02, 46.81it/s] Loading 0: 71%|███████▏ | 259/363 [00:12<00:02, 44.92it/s] Loading 0: 73%|███████▎ | 266/363 [00:12<00:01, 49.65it/s] Loading 0: 75%|███████▍ | 272/363 [00:12<00:01, 46.48it/s] Loading 0: 76%|███████▋ | 277/363 [00:12<00:01, 45.20it/s] Loading 0: 78%|███████▊ | 283/363 [00:12<00:02, 35.99it/s] Loading 0: 79%|███████▉ | 287/363 [00:12<00:02, 35.74it/s] Loading 0: 81%|████████ | 293/363 [00:12<00:01, 39.90it/s] Loading 0: 82%|████████▏ | 299/363 [00:13<00:01, 41.02it/s] Loading 0: 84%|████████▎ | 304/363 [00:13<00:01, 41.63it/s] Loading 0: 85%|████████▌ | 310/363 [00:13<00:01, 45.81it/s] Loading 0: 87%|████████▋ | 315/363 [00:13<00:01, 46.44it/s] Loading 0: 88%|████████▊ | 320/363 [00:13<00:00, 47.39it/s] Loading 0: 90%|████████▉ | 326/363 [00:13<00:00, 44.06it/s] Loading 0: 91%|█████████ | 331/363 [00:13<00:00, 41.52it/s] Loading 0: 93%|█████████▎| 338/363 [00:13<00:00, 46.44it/s] Loading 0: 95%|█████████▍| 344/363 [00:14<00:00, 44.99it/s] Loading 0: 96%|█████████▌| 349/363 [00:14<00:00, 43.17it/s] Loading 0: 98%|█████████▊| 355/363 [00:14<00:00, 46.10it/s] Loading 0: 99%|█████████▉| 360/363 [00:14<00:00, 45.73it/s]
Job yamatazen-ayla-light-12b-v2-v3-mkmlizer completed after 94.07s with status: succeeded
Stopping job with name yamatazen-ayla-light-12b-v2-v3-mkmlizer
Pipeline stage MKMLizer completed in 94.82s
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-v3
Waiting for inference service yamatazen-ayla-light-12b-v2-v3 to be ready
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)
Unable to record family friendly update due to error: Invalid JSON input: JSON must contain 'User Safety' and 'Response Safety' fields
Inference service yamatazen-ayla-light-12b-v2-v3 ready after 371.3876643180847s
Pipeline stage MKMLDeployer completed in 371.91s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.417202949523926s
Received healthy response to inference request in 1.1179742813110352s
Received healthy response to inference request in 1.660404920578003s
Received healthy response to inference request in 1.6918060779571533s
Received healthy response to inference request in 1.4602611064910889s
5 requests
0 failed requests
5th percentile: 1.186431646347046
10th percentile: 1.2548890113830566
20th percentile: 1.3918037414550781
30th percentile: 1.5002898693084716
40th percentile: 1.5803473949432374
50th percentile: 1.660404920578003
60th percentile: 1.6729653835296632
70th percentile: 1.6855258464813232
80th percentile: 1.836885452270508
90th percentile: 2.127044200897217
95th percentile: 2.2721235752105713
99th percentile: 2.388187074661255
mean time: 1.6695298671722412
Pipeline stage StressChecker completed in 9.67s
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 0.65s
Shutdown handler de-registered
yamatazen-ayla-light-12b-v2_v3 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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service yamatazen-ayla-light-12b-v2-v3-profiler
Waiting for inference service yamatazen-ayla-light-12b-v2-v3-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 2520.34s
Shutdown handler de-registered
yamatazen-ayla-light-12b-v2_v3 status is now inactive due to auto deactivation removed underperforming models
yamatazen-ayla-light-12b-v2_v3 status is now torndown due to DeploymentManager action