developer_uid: sy2x20000202
submission_id: ilyagusev-saiga-nemo-12b_v6
model_name: ilyagusev-saiga-nemo-12b_v6
model_group: IlyaGusev/saiga_nemo_12b
status: torndown
timestamp: 2025-01-24T07:52:25+00:00
num_battles: 5376
num_wins: 2505
celo_rating: 1238.57
family_friendly_score: 0.6058
family_friendly_standard_error: 0.006910953045709397
submission_type: basic
model_repo: IlyaGusev/saiga_nemo_12b
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
display_name: ilyagusev-saiga-nemo-12b_v6
is_internal_developer: False
language_model: IlyaGusev/saiga_nemo_12b
model_size: 13B
ranking_group: single
us_pacific_date: 2025-01-23
win_ratio: 0.46595982142857145
generation_params: {'temperature': 0.75, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 20, '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': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{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 ilyagusev-saiga-nemo-12b-v6-mkmlizer
Waiting for job on ilyagusev-saiga-nemo-12b-v6-mkmlizer to finish
ilyagusev-saiga-nemo-12b-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
ilyagusev-saiga-nemo-12b-v6-mkmlizer: ║ _____ __ __ ║
ilyagusev-saiga-nemo-12b-v6-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
ilyagusev-saiga-nemo-12b-v6-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
ilyagusev-saiga-nemo-12b-v6-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
ilyagusev-saiga-nemo-12b-v6-mkmlizer: ║ /___/ ║
ilyagusev-saiga-nemo-12b-v6-mkmlizer: ║ ║
ilyagusev-saiga-nemo-12b-v6-mkmlizer: ║ Version: 0.11.12 ║
ilyagusev-saiga-nemo-12b-v6-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
ilyagusev-saiga-nemo-12b-v6-mkmlizer: ║ https://mk1.ai ║
ilyagusev-saiga-nemo-12b-v6-mkmlizer: ║ ║
ilyagusev-saiga-nemo-12b-v6-mkmlizer: ║ The license key for the current software has been verified as ║
ilyagusev-saiga-nemo-12b-v6-mkmlizer: ║ belonging to: ║
ilyagusev-saiga-nemo-12b-v6-mkmlizer: ║ ║
ilyagusev-saiga-nemo-12b-v6-mkmlizer: ║ Chai Research Corp. ║
ilyagusev-saiga-nemo-12b-v6-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
ilyagusev-saiga-nemo-12b-v6-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
ilyagusev-saiga-nemo-12b-v6-mkmlizer: ║ ║
ilyagusev-saiga-nemo-12b-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
ilyagusev-saiga-nemo-12b-v6-mkmlizer: Downloaded to shared memory in 31.913s
ilyagusev-saiga-nemo-12b-v6-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp0jb35rbz, device:0
ilyagusev-saiga-nemo-12b-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
ilyagusev-saiga-nemo-12b-v6-mkmlizer: quantized model in 38.691s
ilyagusev-saiga-nemo-12b-v6-mkmlizer: Processed model IlyaGusev/saiga_nemo_12b in 70.605s
ilyagusev-saiga-nemo-12b-v6-mkmlizer: creating bucket guanaco-mkml-models
ilyagusev-saiga-nemo-12b-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
ilyagusev-saiga-nemo-12b-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/ilyagusev-saiga-nemo-12b-v6
ilyagusev-saiga-nemo-12b-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/ilyagusev-saiga-nemo-12b-v6/config.json
ilyagusev-saiga-nemo-12b-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/ilyagusev-saiga-nemo-12b-v6/special_tokens_map.json
ilyagusev-saiga-nemo-12b-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/ilyagusev-saiga-nemo-12b-v6/tokenizer_config.json
ilyagusev-saiga-nemo-12b-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/ilyagusev-saiga-nemo-12b-v6/tokenizer.json
ilyagusev-saiga-nemo-12b-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/ilyagusev-saiga-nemo-12b-v6/flywheel_model.0.safetensors
ilyagusev-saiga-nemo-12b-v6-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:12, 28.76it/s] Loading 0: 3%|▎ | 12/363 [00:00<00:07, 44.46it/s] Loading 0: 5%|▍ | 17/363 [00:00<00:08, 40.66it/s] Loading 0: 6%|▌ | 22/363 [00:00<00:09, 36.54it/s] Loading 0: 7%|▋ | 26/363 [00:00<00:09, 36.21it/s] Loading 0: 8%|▊ | 30/363 [00:00<00:09, 36.56it/s] Loading 0: 9%|▉ | 34/363 [00:00<00:09, 35.25it/s] Loading 0: 11%|█ | 39/363 [00:01<00:08, 37.83it/s] Loading 0: 12%|█▏ | 43/363 [00:01<00:08, 36.51it/s] Loading 0: 13%|█▎ | 48/363 [00:01<00:08, 38.50it/s] Loading 0: 14%|█▍ | 52/363 [00:01<00:08, 37.08it/s] Loading 0: 16%|█▌ | 58/363 [00:01<00:07, 42.56it/s] Loading 0: 17%|█▋ | 63/363 [00:01<00:10, 28.90it/s] Loading 0: 18%|█▊ | 67/363 [00:01<00:09, 30.98it/s] Loading 0: 20%|█▉ | 71/363 [00:02<00:09, 30.64it/s] Loading 0: 21%|██ | 75/363 [00:02<00:09, 31.46it/s] Loading 0: 22%|██▏ | 80/363 [00:02<00:07, 35.60it/s] Loading 0: 23%|██▎ | 84/363 [00:02<00:07, 35.40it/s] Loading 0: 25%|██▍ | 89/363 [00:02<00:07, 37.93it/s] Loading 0: 26%|██▌ | 93/363 [00:02<00:07, 36.21it/s] Loading 0: 27%|██▋ | 98/363 [00:02<00:06, 38.75it/s] Loading 0: 28%|██▊ | 102/363 [00:02<00:07, 35.25it/s] Loading 0: 29%|██▉ | 106/363 [00:02<00:07, 35.55it/s] Loading 0: 31%|███ | 112/363 [00:03<00:06, 40.41it/s] Loading 0: 32%|███▏ | 117/363 [00:03<00:06, 38.07it/s] Loading 0: 33%|███▎ | 121/363 [00:03<00:06, 36.38it/s] Loading 0: 34%|███▍ | 125/363 [00:03<00:07, 33.26it/s] Loading 0: 36%|███▌ | 129/363 [00:03<00:06, 33.59it/s] Loading 0: 37%|███▋ | 134/363 [00:03<00:06, 36.49it/s] Loading 0: 38%|███▊ | 138/363 [00:03<00:06, 36.36it/s] Loading 0: 39%|███▉ | 142/363 [00:04<00:09, 22.53it/s] Loading 0: 40%|███▉ | 145/363 [00:04<00:09, 21.93it/s] Loading 0: 41%|████ | 149/363 [00:04<00:09, 22.89it/s] Loading 0: 43%|████▎ | 156/363 [00:04<00:06, 30.91it/s] Loading 0: 44%|████▍ | 160/363 [00:04<00:06, 31.65it/s] Loading 0: 45%|████▌ | 165/363 [00:04<00:05, 34.89it/s] Loading 0: 47%|████▋ | 169/363 [00:04<00:05, 34.41it/s] Loading 0: 48%|████▊ | 173/363 [00:05<00:05, 35.29it/s] Loading 0: 49%|████▉ | 177/363 [00:05<00:06, 30.39it/s] Loading 0: 50%|█████ | 183/363 [00:05<00:05, 35.27it/s] Loading 0: 52%|█████▏ | 187/363 [00:05<00:05, 34.95it/s] Loading 0: 53%|█████▎ | 192/363 [00:05<00:04, 37.70it/s] Loading 0: 54%|█████▍ | 196/363 [00:05<00:04, 36.64it/s] Loading 0: 55%|█████▌ | 201/363 [00:05<00:04, 38.35it/s] Loading 0: 56%|█████▋ | 205/363 [00:05<00:04, 35.24it/s] Loading 0: 58%|█████▊ | 209/363 [00:06<00:04, 35.35it/s] Loading 0: 59%|█████▊ | 213/363 [00:06<00:04, 31.80it/s] Loading 0: 60%|██████ | 218/363 [00:06<00:04, 34.62it/s] Loading 0: 61%|██████ | 222/363 [00:06<00:03, 35.60it/s] Loading 0: 62%|██████▏ | 226/363 [00:06<00:06, 20.25it/s] Loading 0: 63%|██████▎ | 230/363 [00:07<00:06, 21.66it/s] Loading 0: 65%|██████▌ | 237/363 [00:07<00:04, 29.16it/s] Loading 0: 66%|██████▋ | 241/363 [00:07<00:04, 30.29it/s] Loading 0: 68%|██████▊ | 246/363 [00:07<00:03, 33.37it/s] Loading 0: 69%|██████▉ | 250/363 [00:07<00:03, 33.70it/s] Loading 0: 70%|███████ | 255/363 [00:07<00:02, 36.21it/s] Loading 0: 71%|███████▏ | 259/363 [00:07<00:02, 35.83it/s] Loading 0: 73%|███████▎ | 264/363 [00:07<00:02, 38.77it/s] Loading 0: 74%|███████▍ | 269/363 [00:07<00:02, 39.06it/s] Loading 0: 75%|███████▌ | 274/363 [00:08<00:02, 39.85it/s] Loading 0: 77%|███████▋ | 279/363 [00:08<00:02, 41.61it/s] Loading 0: 78%|███████▊ | 284/363 [00:08<00:02, 33.68it/s] Loading 0: 80%|████████ | 291/363 [00:08<00:01, 40.35it/s] Loading 0: 82%|████████▏ | 296/363 [00:08<00:01, 40.79it/s] Loading 0: 83%|████████▎ | 301/363 [00:08<00:01, 42.79it/s] Loading 0: 84%|████████▍ | 306/363 [00:15<00:24, 2.32it/s] Loading 0: 85%|████████▌ | 310/363 [00:16<00:17, 3.01it/s] Loading 0: 87%|████████▋ | 314/363 [00:16<00:12, 3.95it/s] Loading 0: 88%|████████▊ | 320/363 [00:16<00:07, 5.93it/s] Loading 0: 90%|████████▉ | 326/363 [00:16<00:04, 8.29it/s] Loading 0: 91%|█████████ | 330/363 [00:16<00:03, 10.14it/s] Loading 0: 93%|█████████▎| 338/363 [00:16<00:01, 15.67it/s] Loading 0: 95%|█████████▍| 344/363 [00:16<00:01, 18.92it/s] Loading 0: 96%|█████████▌| 349/363 [00:17<00:00, 21.34it/s] Loading 0: 98%|█████████▊| 354/363 [00:17<00:00, 25.01it/s] Loading 0: 99%|█████████▉| 359/363 [00:17<00:00, 27.08it/s]
Job ilyagusev-saiga-nemo-12b-v6-mkmlizer completed after 104.11s with status: succeeded
Stopping job with name ilyagusev-saiga-nemo-12b-v6-mkmlizer
Pipeline stage MKMLizer completed in 104.55s
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 ilyagusev-saiga-nemo-12b-v6
Waiting for inference service ilyagusev-saiga-nemo-12b-v6 to be ready
Inference service ilyagusev-saiga-nemo-12b-v6 ready after 160.54300904273987s
Pipeline stage MKMLDeployer completed in 160.96s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0847442150115967s
Received healthy response to inference request in 1.668367624282837s
Received healthy response to inference request in 1.8211407661437988s
Received healthy response to inference request in 2.239211320877075s
Received healthy response to inference request in 1.8804869651794434s
5 requests
0 failed requests
5th percentile: 1.6989222526550294
10th percentile: 1.7294768810272216
20th percentile: 1.7905861377716064
30th percentile: 1.8330100059509278
40th percentile: 1.8567484855651855
50th percentile: 1.8804869651794434
60th percentile: 1.9621898651123046
70th percentile: 2.043892765045166
80th percentile: 2.1156376361846925
90th percentile: 2.1774244785308836
95th percentile: 2.2083178997039794
99th percentile: 2.233032636642456
mean time: 1.9387901782989503
Pipeline stage StressChecker completed in 10.93s
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 0.59s
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
ilyagusev-saiga-nemo-12b_v6 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 3527.03s
Shutdown handler de-registered
ilyagusev-saiga-nemo-12b_v6 status is now inactive due to auto deactivation removed underperforming models
ilyagusev-saiga-nemo-12b_v6 status is now torndown due to DeploymentManager action