developer_uid: azuruce
submission_id: chaiml-nemo-all-10_v1
model_name: chaiml-nemo-all-10_v1
model_group: ChaiML/nemo-all-10
status: torndown
timestamp: 2024-10-01T02:00:49+00:00
num_battles: 3960
num_wins: 2027
celo_rating: 1261.29
family_friendly_score: 0.570784908202796
family_friendly_standard_error: 0.007844208965703882
submission_type: basic
model_repo: ChaiML/nemo-all-10
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
display_name: chaiml-nemo-all-10_v1
ineligible_reason: num_battles<5000
is_internal_developer: True
language_model: ChaiML/nemo-all-10
model_size: 13B
ranking_group: single
us_pacific_date: 2024-09-30
win_ratio: 0.5118686868686869
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': '', 'prompt_template': '', '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-nemo-all-10-v1-mkmlizer
Waiting for job on chaiml-nemo-all-10-v1-mkmlizer to finish
chaiml-nemo-all-10-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-all-10-v1-mkmlizer: ║ _____ __ __ ║
chaiml-nemo-all-10-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-nemo-all-10-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-nemo-all-10-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-nemo-all-10-v1-mkmlizer: ║ /___/ ║
chaiml-nemo-all-10-v1-mkmlizer: ║ ║
chaiml-nemo-all-10-v1-mkmlizer: ║ Version: 0.11.12 ║
chaiml-nemo-all-10-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-nemo-all-10-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-nemo-all-10-v1-mkmlizer: ║ ║
chaiml-nemo-all-10-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-nemo-all-10-v1-mkmlizer: ║ belonging to: ║
chaiml-nemo-all-10-v1-mkmlizer: ║ ║
chaiml-nemo-all-10-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-nemo-all-10-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-nemo-all-10-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-nemo-all-10-v1-mkmlizer: ║ ║
chaiml-nemo-all-10-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-all-10-v1-mkmlizer: Downloaded to shared memory in 46.570s
chaiml-nemo-all-10-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmppegahqh_, device:0
chaiml-nemo-all-10-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-all-10-v1-mkmlizer: quantized model in 35.220s
chaiml-nemo-all-10-v1-mkmlizer: Processed model ChaiML/nemo-all-10 in 81.790s
chaiml-nemo-all-10-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-all-10-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-all-10-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-all-10-v1
chaiml-nemo-all-10-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-all-10-v1/config.json
chaiml-nemo-all-10-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-all-10-v1/special_tokens_map.json
chaiml-nemo-all-10-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-all-10-v1/tokenizer_config.json
chaiml-nemo-all-10-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-all-10-v1/tokenizer.json
chaiml-nemo-all-10-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-all-10-v1/flywheel_model.0.safetensors
chaiml-nemo-all-10-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 2/363 [00:05<17:35, 2.92s/it] Loading 0: 2%|▏ | 6/363 [00:06<04:42, 1.26it/s] Loading 0: 4%|▎ | 13/363 [00:06<01:40, 3.47it/s] Loading 0: 5%|▍ | 17/363 [00:06<01:08, 5.06it/s] Loading 0: 6%|▋ | 23/363 [00:06<00:41, 8.28it/s] Loading 0: 8%|▊ | 29/363 [00:06<00:28, 11.81it/s] Loading 0: 9%|▉ | 34/363 [00:06<00:21, 15.18it/s] Loading 0: 11%|█ | 40/363 [00:06<00:18, 17.73it/s] Loading 0: 12%|█▏ | 44/363 [00:06<00:15, 20.35it/s] Loading 0: 14%|█▍ | 50/363 [00:07<00:11, 26.30it/s] Loading 0: 15%|█▌ | 56/363 [00:07<00:10, 30.31it/s] Loading 0: 17%|█▋ | 61/363 [00:07<00:09, 33.20it/s] Loading 0: 19%|█▊ | 68/363 [00:07<00:07, 40.02it/s] Loading 0: 20%|██ | 74/363 [00:07<00:07, 40.25it/s] Loading 0: 22%|██▏ | 79/363 [00:07<00:07, 38.49it/s] Loading 0: 23%|██▎ | 85/363 [00:07<00:06, 42.99it/s] Loading 0: 25%|██▍ | 90/363 [00:07<00:06, 43.43it/s] Loading 0: 26%|██▌ | 95/363 [00:08<00:06, 44.25it/s] Loading 0: 28%|██▊ | 101/363 [00:08<00:05, 44.59it/s] Loading 0: 29%|██▉ | 106/363 [00:08<00:05, 44.45it/s] Loading 0: 31%|███ | 112/363 [00:08<00:05, 47.49it/s] Loading 0: 32%|███▏ | 117/363 [00:08<00:05, 43.26it/s] Loading 0: 34%|███▎ | 122/363 [00:08<00:07, 30.42it/s] Loading 0: 35%|███▍ | 126/363 [00:08<00:07, 32.28it/s] Loading 0: 36%|███▋ | 132/363 [00:09<00:06, 33.75it/s] Loading 0: 39%|███▊ | 140/363 [00:09<00:05, 42.03it/s] Loading 0: 40%|███▉ | 145/363 [00:09<00:04, 43.64it/s] Loading 0: 41%|████▏ | 150/363 [00:09<00:05, 37.51it/s] Loading 0: 44%|████▎ | 158/363 [00:09<00:04, 45.69it/s] Loading 0: 45%|████▌ | 164/363 [00:09<00:04, 45.72it/s] Loading 0: 47%|████▋ | 169/363 [00:09<00:04, 43.89it/s] Loading 0: 48%|████▊ | 175/363 [00:09<00:03, 47.27it/s] Loading 0: 50%|████▉ | 180/363 [00:10<00:03, 47.53it/s] Loading 0: 51%|█████ | 186/363 [00:10<00:04, 42.75it/s] Loading 0: 53%|█████▎ | 194/363 [00:10<00:03, 50.68it/s] Loading 0: 55%|█████▌ | 200/363 [00:10<00:03, 48.14it/s] Loading 0: 57%|█████▋ | 206/363 [00:10<00:04, 34.48it/s] Loading 0: 58%|█████▊ | 212/363 [00:10<00:03, 38.45it/s] Loading 0: 60%|██████ | 218/363 [00:11<00:03, 37.99it/s] Loading 0: 61%|██████▏ | 223/363 [00:11<00:03, 37.37it/s] Loading 0: 63%|██████▎ | 229/363 [00:11<00:03, 41.23it/s] Loading 0: 64%|██████▍ | 234/363 [00:11<00:03, 42.04it/s] Loading 0: 66%|██████▌ | 239/363 [00:11<00:02, 42.80it/s] Loading 0: 67%|██████▋ | 244/363 [00:11<00:02, 43.75it/s] Loading 0: 69%|██████▊ | 249/363 [00:11<00:02, 38.17it/s] Loading 0: 71%|███████ | 257/363 [00:11<00:02, 47.08it/s] Loading 0: 72%|███████▏ | 263/363 [00:12<00:02, 45.27it/s] Loading 0: 74%|███████▍ | 268/363 [00:12<00:02, 42.63it/s] Loading 0: 75%|███████▌ | 274/363 [00:12<00:01, 46.59it/s] Loading 0: 77%|███████▋ | 279/363 [00:12<00:01, 44.99it/s] Loading 0: 78%|███████▊ | 284/363 [00:12<00:02, 32.78it/s] Loading 0: 80%|███████▉ | 289/363 [00:12<00:02, 36.03it/s] Loading 0: 81%|████████ | 294/363 [00:12<00:02, 33.36it/s] Loading 0: 83%|████████▎ | 302/363 [00:13<00:01, 41.61it/s] Loading 0: 85%|████████▍ | 307/363 [00:13<00:01, 42.09it/s] Loading 0: 86%|████████▌ | 312/363 [00:13<00:01, 35.91it/s] Loading 0: 88%|████████▊ | 320/363 [00:13<00:00, 43.65it/s] Loading 0: 90%|████████▉ | 326/363 [00:13<00:00, 42.10it/s] Loading 0: 91%|█████████ | 331/363 [00:13<00:00, 41.60it/s] Loading 0: 93%|█████████▎| 338/363 [00:13<00:00, 46.50it/s] Loading 0: 95%|█████████▍| 344/363 [00:14<00:00, 45.21it/s] Loading 0: 96%|█████████▌| 349/363 [00:14<00:00, 44.13it/s] Loading 0: 98%|█████████▊| 356/363 [00:14<00:00, 48.62it/s] Loading 0: 100%|█████████▉| 362/363 [00:14<00:00, 45.37it/s]
Job chaiml-nemo-all-10-v1-mkmlizer completed after 103.22s with status: succeeded
Stopping job with name chaiml-nemo-all-10-v1-mkmlizer
Pipeline stage MKMLizer completed in 104.09s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nemo-all-10-v1
Waiting for inference service chaiml-nemo-all-10-v1 to be ready
Inference service chaiml-nemo-all-10-v1 ready after 140.56983613967896s
Pipeline stage MKMLDeployer completed in 140.94s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2185871601104736s
Received healthy response to inference request in 1.548799991607666s
Received healthy response to inference request in 1.6037962436676025s
Received healthy response to inference request in 1.4573090076446533s
Received healthy response to inference request in 1.6195487976074219s
5 requests
0 failed requests
5th percentile: 1.475607204437256
10th percentile: 1.4939054012298585
20th percentile: 1.5305017948150634
30th percentile: 1.5597992420196534
40th percentile: 1.5817977428436278
50th percentile: 1.6037962436676025
60th percentile: 1.6100972652435304
70th percentile: 1.616398286819458
80th percentile: 1.7393564701080324
90th percentile: 1.978971815109253
95th percentile: 2.098779487609863
99th percentile: 2.1946256256103513
mean time: 1.6896082401275634
Pipeline stage StressChecker completed in 9.05s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 4.31s
Shutdown handler de-registered
chaiml-nemo-all-10_v1 status is now deployed due to DeploymentManager action
chaiml-nemo-all-10_v1 status is now inactive due to auto deactivation removed underperforming models
Pipeline stage MKMLModelDeleter completed in 3.49s
admin requested tearing down of chaiml-nemo-comm-2bbio-m_2877_v1
chaiml-nemo-all-10_v1 status is now torndown due to DeploymentManager action
run pipeline %s
Shutdown handler de-registered
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of chaiml-nemo-comm-2blinea_9021_v1