alexxi19-ft-nemo-base-lora

developer_uid: leosheng

submission_id: alexxi19-ft-nemo-base-lora_v6

model_name: alexxi19-ft-nemo-base-lora_v6

model_group: alexxi19/ft-nemo-base-lo

status: torndown

timestamp: 2025-02-20T03:06:29+00:00

num_battles: 5372

num_wins: 2581

celo_rating: 1249.12

family_friendly_score: 0.5622

family_friendly_standard_error: 0.007016140819567407

submission_type: basic

model_repo: alexxi19/ft-nemo-base-lora

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6004300714607732, 'latency_mean': 1.6654031813144683, 'latency_p50': 1.654314637184143, 'latency_p90': 1.8389005661010742}, {'batch_size': 3, 'throughput': 1.0971205766642098, 'latency_mean': 2.728834674358368, 'latency_p50': 2.73730206489563, 'latency_p90': 2.969001841545105}, {'batch_size': 5, 'throughput': 1.3311694796247555, 'latency_mean': 3.7436403679847716, 'latency_p50': 3.7780948877334595, 'latency_p90': 4.193274188041687}, {'batch_size': 6, 'throughput': 1.3827871705331094, 'latency_mean': 4.321497403383255, 'latency_p50': 4.289355635643005, 'latency_p90': 4.831761336326599}, {'batch_size': 8, 'throughput': 1.4528138224585614, 'latency_mean': 5.470748862028122, 'latency_p50': 5.508264780044556, 'latency_p90': 6.164558672904969}, {'batch_size': 10, 'throughput': 1.4833816148366228, 'latency_mean': 6.6920131492614745, 'latency_p50': 6.731922745704651, 'latency_p90': 7.470448064804076}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: alexxi19-ft-nemo-base-lora_v6

is_internal_developer: False

language_model: alexxi19/ft-nemo-base-lora

model_size: 13B

ranking_group: single

throughput_3p7s: 1.33

us_pacific_date: 2025-02-19

win_ratio: 0.4804542069992554

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': '<|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 alexxi19-ft-nemo-base-lora-v6-mkmlizer
Waiting for job on alexxi19-ft-nemo-base-lora-v6-mkmlizer to finish
alexxi19-ft-nemo-base-lora-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexxi19-ft-nemo-base-lora-v6-mkmlizer: ║     _____            __           __                                ║
alexxi19-ft-nemo-base-lora-v6-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
alexxi19-ft-nemo-base-lora-v6-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
alexxi19-ft-nemo-base-lora-v6-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
alexxi19-ft-nemo-base-lora-v6-mkmlizer: ║       /___/                                                         ║
alexxi19-ft-nemo-base-lora-v6-mkmlizer: ║                                                                     ║
alexxi19-ft-nemo-base-lora-v6-mkmlizer: ║  Version: 0.12.8                                                    ║
alexxi19-ft-nemo-base-lora-v6-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
alexxi19-ft-nemo-base-lora-v6-mkmlizer: ║  https://mk1.ai                                                     ║
alexxi19-ft-nemo-base-lora-v6-mkmlizer: ║                                                                     ║
alexxi19-ft-nemo-base-lora-v6-mkmlizer: ║  The license key for the current software has been verified as      ║
alexxi19-ft-nemo-base-lora-v6-mkmlizer: ║  belonging to:                                                      ║
alexxi19-ft-nemo-base-lora-v6-mkmlizer: ║                                                                     ║
alexxi19-ft-nemo-base-lora-v6-mkmlizer: ║  Chai Research Corp.                                                ║
alexxi19-ft-nemo-base-lora-v6-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
alexxi19-ft-nemo-base-lora-v6-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
alexxi19-ft-nemo-base-lora-v6-mkmlizer: ║                                                                     ║
alexxi19-ft-nemo-base-lora-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission mistralai-mistral-nem_93303_v390: ('http://mistralai-mistral-nem-93303-v390-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:58884->127.0.0.1:8080: read: connection reset by peer\n')
alexxi19-ft-nemo-base-lora-v6-mkmlizer: Downloaded to shared memory in 61.128s
alexxi19-ft-nemo-base-lora-v6-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp5pc13hyj, device:0
alexxi19-ft-nemo-base-lora-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alexxi19-ft-nemo-base-lora-v6-mkmlizer: quantized model in 39.069s
alexxi19-ft-nemo-base-lora-v6-mkmlizer: Processed model alexxi19/ft-nemo-base-lora in 100.198s
alexxi19-ft-nemo-base-lora-v6-mkmlizer: creating bucket guanaco-mkml-models
alexxi19-ft-nemo-base-lora-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexxi19-ft-nemo-base-lora-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexxi19-ft-nemo-base-lora-v6
alexxi19-ft-nemo-base-lora-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alexxi19-ft-nemo-base-lora-v6/config.json
alexxi19-ft-nemo-base-lora-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alexxi19-ft-nemo-base-lora-v6/special_tokens_map.json
alexxi19-ft-nemo-base-lora-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexxi19-ft-nemo-base-lora-v6/tokenizer_config.json
alexxi19-ft-nemo-base-lora-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexxi19-ft-nemo-base-lora-v6/tokenizer.json
alexxi19-ft-nemo-base-lora-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alexxi19-ft-nemo-base-lora-v6/flywheel_model.0.safetensors
alexxi19-ft-nemo-base-lora-v6-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 27.58it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:08, 41.86it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:09, 37.58it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:08, 39.01it/s]
Loading 0:   7%|▋         | 26/363 [00:00<00:08, 38.10it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:08, 37.10it/s]
Loading 0:   9%|▉         | 34/363 [00:00<00:09, 35.18it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:08, 37.22it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:08, 35.62it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:08, 37.65it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:08, 35.50it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:08, 34.74it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:12, 25.12it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:12, 23.70it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:10, 28.63it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:10, 28.24it/s]
Loading 0:  21%|██▏       | 78/363 [00:02<00:08, 32.86it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:08, 31.26it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:07, 35.59it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:08, 32.89it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:06, 39.77it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:06, 38.96it/s]
Loading 0:  30%|██▉       | 108/363 [00:03<00:06, 40.19it/s]
Loading 0:  31%|███       | 113/363 [00:03<00:07, 33.43it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:07, 33.49it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:06, 39.32it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:06, 38.22it/s]
Loading 0:  37%|███▋      | 134/363 [00:03<00:06, 35.56it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 34.05it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:09, 24.15it/s]
Loading 0:  40%|███▉      | 145/363 [00:04<00:09, 23.99it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:08, 24.71it/s]
Loading 0:  42%|████▏     | 154/363 [00:04<00:07, 29.76it/s]
Loading 0:  44%|████▎     | 158/363 [00:04<00:07, 28.58it/s]
Loading 0:  45%|████▍     | 163/363 [00:04<00:06, 33.27it/s]
Loading 0:  46%|████▌     | 167/363 [00:05<00:06, 31.02it/s]
Loading 0:  47%|████▋     | 172/363 [00:05<00:05, 35.19it/s]
Loading 0:  48%|████▊     | 176/363 [00:05<00:05, 31.72it/s]
Loading 0:  50%|████▉     | 181/363 [00:05<00:05, 35.86it/s]
Loading 0:  51%|█████     | 185/363 [00:05<00:05, 32.13it/s]
Loading 0:  52%|█████▏    | 190/363 [00:05<00:04, 35.56it/s]
Loading 0:  53%|█████▎    | 194/363 [00:05<00:05, 32.54it/s]
Loading 0:  55%|█████▍    | 199/363 [00:05<00:04, 36.65it/s]
Loading 0:  56%|█████▌    | 203/363 [00:06<00:04, 32.11it/s]
Loading 0:  57%|█████▋    | 208/363 [00:06<00:04, 35.83it/s]
Loading 0:  58%|█████▊    | 212/363 [00:06<00:04, 32.33it/s]
Loading 0:  60%|█████▉    | 217/363 [00:06<00:04, 35.91it/s]
Loading 0:  61%|██████    | 222/363 [00:06<00:03, 36.69it/s]
Loading 0:  62%|██████▏   | 226/363 [00:06<00:05, 23.29it/s]
Loading 0:  63%|██████▎   | 230/363 [00:07<00:05, 23.69it/s]
Loading 0:  65%|██████▍   | 235/363 [00:07<00:04, 28.17it/s]
Loading 0:  66%|██████▌   | 239/363 [00:07<00:04, 27.28it/s]
Loading 0:  67%|██████▋   | 244/363 [00:07<00:03, 31.59it/s]
Loading 0:  68%|██████▊   | 248/363 [00:07<00:03, 29.77it/s]
Loading 0:  70%|██████▉   | 253/363 [00:07<00:03, 34.09it/s]
Loading 0:  71%|███████   | 257/363 [00:07<00:03, 31.33it/s]
Loading 0:  72%|███████▏  | 262/363 [00:08<00:02, 35.24it/s]
Loading 0:  73%|███████▎  | 266/363 [00:08<00:02, 32.40it/s]
Loading 0:  75%|███████▍  | 271/363 [00:08<00:02, 36.28it/s]
Loading 0:  76%|███████▌  | 275/363 [00:08<00:02, 32.62it/s]
Loading 0:  77%|███████▋  | 280/363 [00:08<00:02, 36.47it/s]
Loading 0:  78%|███████▊  | 284/363 [00:08<00:02, 32.97it/s]
Loading 0:  80%|███████▉  | 289/363 [00:08<00:02, 36.50it/s]
Loading 0:  81%|████████  | 293/363 [00:08<00:02, 32.59it/s]
Loading 0:  82%|████████▏ | 298/363 [00:09<00:01, 36.61it/s]
Loading 0:  83%|████████▎ | 303/363 [00:09<00:01, 37.37it/s]
Loading 0:  85%|████████▍ | 307/363 [00:16<00:27,  2.07it/s]
Loading 0:  86%|████████▌ | 312/363 [00:16<00:17,  2.97it/s]
Loading 0:  87%|████████▋ | 317/363 [00:16<00:10,  4.22it/s]
Loading 0:  88%|████████▊ | 321/363 [00:16<00:07,  5.42it/s]
Loading 0:  90%|█████████ | 328/363 [00:16<00:04,  8.48it/s]
Loading 0:  91%|█████████▏| 332/363 [00:16<00:03, 10.33it/s]
Loading 0:  93%|█████████▎| 337/363 [00:16<00:01, 13.45it/s]
Loading 0:  94%|█████████▍| 341/363 [00:17<00:01, 15.82it/s]
Loading 0:  95%|█████████▌| 346/363 [00:17<00:00, 19.79it/s]
Loading 0:  96%|█████████▋| 350/363 [00:17<00:00, 21.98it/s]
Loading 0:  98%|█████████▊| 355/363 [00:17<00:00, 26.01it/s]
Loading 0:  99%|█████████▉| 359/363 [00:17<00:00, 27.35it/s]
                                                            
Job alexxi19-ft-nemo-base-lora-v6-mkmlizer completed after 124.99s with status: succeeded
Stopping job with name alexxi19-ft-nemo-base-lora-v6-mkmlizer
Pipeline stage MKMLizer completed in 125.53s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service alexxi19-ft-nemo-base-lora-v6
Waiting for inference service alexxi19-ft-nemo-base-lora-v6 to be ready
Inference service alexxi19-ft-nemo-base-lora-v6 ready after 180.81789135932922s
Pipeline stage MKMLDeployer completed in 181.40s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5165419578552246s
Received healthy response to inference request in 1.655280590057373s
Received healthy response to inference request in 1.7570250034332275s
Received healthy response to inference request in 1.6507024765014648s
Received healthy response to inference request in 1.6154406070709229s
5 requests
0 failed requests
5th percentile: 1.6224929809570312
10th percentile: 1.6295453548431396
20th percentile: 1.6436501026153565
30th percentile: 1.6516180992126466
40th percentile: 1.6534493446350098
50th percentile: 1.655280590057373
60th percentile: 1.6959783554077148
70th percentile: 1.7366761207580566
80th percentile: 1.9089283943176272
90th percentile: 2.212735176086426
95th percentile: 2.364638566970825
99th percentile: 2.4861612796783445
mean time: 1.8389981269836426
Pipeline stage StressChecker completed in 10.61s
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 0.87s
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
alexxi19-ft-nemo-base-lora_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 2530.21s
Shutdown handler de-registered
alexxi19-ft-nemo-base-lora_v6 status is now inactive due to auto deactivation removed underperforming models
alexxi19-ft-nemo-base-lora_v6 status is now torndown due to DeploymentManager action
alexxi19-ft-nemo-base-lora_v6 status is now torndown due to DeploymentManager action
alexxi19-ft-nemo-base-lora_v6 status is now torndown due to DeploymentManager action