alexxi19-ft-v1-nemo-ba_27407

developer_uid: azuruce

submission_id: alexxi19-ft-v1-nemo-ba_27407_v19

model_name: alexxi19-ft-v1-nemo-ba_27407_v19

model_group: alexxi19/ft-v1-nemo-base

status: torndown

timestamp: 2025-02-25T19:09:14+00:00

num_battles: 5989

num_wins: 2993

celo_rating: 1270.82

family_friendly_score: 0.5558000000000001

family_friendly_standard_error: 0.0070268963276826565

submission_type: basic

model_repo: alexxi19/ft-v1-nemo-base-merge-v1

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 768

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.6351933490826494, 'latency_mean': 1.5742266511917113, 'latency_p50': 1.5745545625686646, 'latency_p90': 1.7388164758682252}, {'batch_size': 3, 'throughput': 1.2071947871488993, 'latency_mean': 2.478653825521469, 'latency_p50': 2.484063148498535, 'latency_p90': 2.733805251121521}, {'batch_size': 5, 'throughput': 1.477812481989475, 'latency_mean': 3.3635615408420563, 'latency_p50': 3.356705069541931, 'latency_p90': 3.7533725261688233}, {'batch_size': 6, 'throughput': 1.5553361201522429, 'latency_mean': 3.8375893354415895, 'latency_p50': 3.816939353942871, 'latency_p90': 4.349388694763183}, {'batch_size': 8, 'throughput': 1.6416619277421174, 'latency_mean': 4.836476358175278, 'latency_p50': 4.7674031257629395, 'latency_p90': 5.460938596725464}, {'batch_size': 10, 'throughput': 1.6913058676767352, 'latency_mean': 5.869583958387375, 'latency_p50': 5.9103240966796875, 'latency_p90': 6.650831842422485}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: alexxi19-ft-v1-nemo-ba_27407_v19

is_internal_developer: False

language_model: alexxi19/ft-v1-nemo-base-merge-v1

model_size: 13B

ranking_group: single

throughput_3p7s: 1.54

us_pacific_date: 2025-02-25

win_ratio: 0.4997495408248456

generation_params: {'temperature': 0.8, 'top_p': 0.9, 'min_p': 0.1, 'top_k': 55, 'presence_penalty': 0.7, 'frequency_penalty': 0.2, 'stopping_words': ['\n'], 'max_input_tokens': 768, '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-v1-nemo-ba-27407-v19-mkmlizer
Waiting for job on alexxi19-ft-v1-nemo-ba-27407-v19-mkmlizer to finish
alexxi19-ft-v1-nemo-ba-27407-v19-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexxi19-ft-v1-nemo-ba-27407-v19-mkmlizer: ║     _____            __           __                                ║
alexxi19-ft-v1-nemo-ba-27407-v19-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
alexxi19-ft-v1-nemo-ba-27407-v19-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
alexxi19-ft-v1-nemo-ba-27407-v19-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
alexxi19-ft-v1-nemo-ba-27407-v19-mkmlizer: ║       /___/                                                         ║
alexxi19-ft-v1-nemo-ba-27407-v19-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-ba-27407-v19-mkmlizer: ║  Version: 0.12.8                                                    ║
alexxi19-ft-v1-nemo-ba-27407-v19-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
alexxi19-ft-v1-nemo-ba-27407-v19-mkmlizer: ║  https://mk1.ai                                                     ║
alexxi19-ft-v1-nemo-ba-27407-v19-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-ba-27407-v19-mkmlizer: ║  The license key for the current software has been verified as      ║
alexxi19-ft-v1-nemo-ba-27407-v19-mkmlizer: ║  belonging to:                                                      ║
alexxi19-ft-v1-nemo-ba-27407-v19-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-ba-27407-v19-mkmlizer: ║  Chai Research Corp.                                                ║
alexxi19-ft-v1-nemo-ba-27407-v19-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
alexxi19-ft-v1-nemo-ba-27407-v19-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
alexxi19-ft-v1-nemo-ba-27407-v19-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-ba-27407-v19-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alexxi19-ft-v1-nemo-ba-27407-v19-mkmlizer: Downloaded to shared memory in 131.972s
alexxi19-ft-v1-nemo-ba-27407-v19-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_mrl86qr, device:0
alexxi19-ft-v1-nemo-ba-27407-v19-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alexxi19-ft-v1-nemo-ba-27407-v19-mkmlizer: quantized model in 35.634s
alexxi19-ft-v1-nemo-ba-27407-v19-mkmlizer: Processed model alexxi19/ft-v1-nemo-base-merge-v1 in 167.607s
alexxi19-ft-v1-nemo-ba-27407-v19-mkmlizer: creating bucket guanaco-mkml-models
alexxi19-ft-v1-nemo-ba-27407-v19-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexxi19-ft-v1-nemo-ba-27407-v19-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v19
alexxi19-ft-v1-nemo-ba-27407-v19-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v19/config.json
alexxi19-ft-v1-nemo-ba-27407-v19-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v19/special_tokens_map.json
alexxi19-ft-v1-nemo-ba-27407-v19-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v19/tokenizer_config.json
alexxi19-ft-v1-nemo-ba-27407-v19-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v19/tokenizer.json
alexxi19-ft-v1-nemo-ba-27407-v19-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v19/flywheel_model.0.safetensors
alexxi19-ft-v1-nemo-ba-27407-v19-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:09,  3.02s/it]
Loading 0:   1%|          | 3/363 [00:06<10:52,  1.81s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:03,  1.47it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:19,  4.39it/s]
Loading 0:   5%|▍         | 18/363 [00:06<00:51,  6.74it/s]
Loading 0:   6%|▋         | 23/363 [00:06<00:34,  9.90it/s]
Loading 0:   8%|▊         | 29/363 [00:06<00:23, 14.15it/s]
Loading 0:   9%|▉         | 33/363 [00:07<00:21, 15.69it/s]
Loading 0:  11%|█▏        | 41/363 [00:07<00:13, 23.87it/s]
Loading 0:  13%|█▎        | 47/363 [00:07<00:11, 27.82it/s]
Loading 0:  14%|█▍        | 52/363 [00:07<00:11, 27.66it/s]
Loading 0:  16%|█▋        | 59/363 [00:07<00:08, 34.72it/s]
Loading 0:  18%|█▊        | 65/363 [00:07<00:08, 37.03it/s]
Loading 0:  19%|█▉        | 70/363 [00:07<00:08, 34.01it/s]
Loading 0:  21%|██        | 77/363 [00:07<00:07, 40.50it/s]
Loading 0:  23%|██▎       | 82/363 [00:08<00:07, 38.13it/s]
Loading 0:  24%|██▍       | 87/363 [00:08<00:07, 35.84it/s]
Loading 0:  26%|██▌       | 95/363 [00:08<00:06, 44.43it/s]
Loading 0:  28%|██▊       | 100/363 [00:08<00:06, 39.39it/s]
Loading 0:  29%|██▉       | 105/363 [00:08<00:07, 36.36it/s]
Loading 0:  31%|███       | 113/363 [00:08<00:06, 39.11it/s]
Loading 0:  33%|███▎      | 119/363 [00:09<00:06, 40.32it/s]
Loading 0:  34%|███▍      | 124/363 [00:09<00:05, 40.25it/s]
Loading 0:  36%|███▌      | 130/363 [00:09<00:06, 38.06it/s]
Loading 0:  37%|███▋      | 134/363 [00:09<00:06, 37.55it/s]
Loading 0:  39%|███▊      | 140/363 [00:09<00:05, 41.75it/s]
Loading 0:  40%|███▉      | 145/363 [00:09<00:05, 37.51it/s]
Loading 0:  41%|████      | 149/363 [00:09<00:05, 37.71it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:05, 40.47it/s]
Loading 0:  44%|████▍     | 159/363 [00:10<00:06, 30.77it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:04, 39.59it/s]
Loading 0:  48%|████▊     | 173/363 [00:10<00:04, 40.50it/s]
Loading 0:  49%|████▉     | 178/363 [00:10<00:05, 35.73it/s]
Loading 0:  51%|█████     | 185/363 [00:10<00:04, 42.42it/s]
Loading 0:  53%|█████▎    | 191/363 [00:10<00:03, 43.12it/s]
Loading 0:  54%|█████▍    | 196/363 [00:11<00:04, 36.81it/s]
Loading 0:  56%|█████▌    | 203/363 [00:11<00:03, 43.23it/s]
Loading 0:  57%|█████▋    | 208/363 [00:11<00:03, 39.99it/s]
Loading 0:  59%|█████▊    | 213/363 [00:11<00:04, 36.74it/s]
Loading 0:  61%|██████    | 221/363 [00:11<00:03, 45.11it/s]
Loading 0:  62%|██████▏   | 226/363 [00:11<00:03, 40.71it/s]
Loading 0:  64%|██████▎   | 231/363 [00:11<00:03, 37.06it/s]
Loading 0:  66%|██████▌   | 239/363 [00:12<00:03, 39.53it/s]
Loading 0:  67%|██████▋   | 245/363 [00:12<00:02, 41.17it/s]
Loading 0:  69%|██████▉   | 250/363 [00:12<00:02, 42.00it/s]
Loading 0:  71%|███████   | 256/363 [00:12<00:02, 40.08it/s]
Loading 0:  72%|███████▏  | 261/363 [00:12<00:02, 41.95it/s]
Loading 0:  74%|███████▎  | 267/363 [00:12<00:02, 40.29it/s]
Loading 0:  75%|███████▍  | 272/363 [00:12<00:02, 39.28it/s]
Loading 0:  76%|███████▌  | 276/363 [00:13<00:02, 38.06it/s]
Loading 0:  78%|███████▊  | 284/363 [00:13<00:01, 47.16it/s]
Loading 0:  80%|███████▉  | 289/363 [00:13<00:01, 41.63it/s]
Loading 0:  81%|████████  | 294/363 [00:13<00:01, 37.19it/s]
Loading 0:  83%|████████▎ | 302/363 [00:13<00:01, 39.33it/s]
Loading 0:  85%|████████▍ | 308/363 [00:13<00:01, 40.25it/s]
Loading 0:  86%|████████▌ | 313/363 [00:13<00:01, 40.85it/s]
Loading 0:  88%|████████▊ | 319/363 [00:14<00:01, 39.68it/s]
Loading 0:  89%|████████▉ | 324/363 [00:14<00:00, 41.66it/s]
Loading 0:  91%|█████████ | 330/363 [00:14<00:00, 39.69it/s]
Loading 0:  92%|█████████▏| 335/363 [00:14<00:00, 39.01it/s]
Loading 0:  93%|█████████▎| 339/363 [00:14<00:00, 37.86it/s]
Loading 0:  96%|█████████▌| 347/363 [00:14<00:00, 47.06it/s]
Loading 0:  97%|█████████▋| 352/363 [00:14<00:00, 41.24it/s]
Loading 0:  98%|█████████▊| 357/363 [00:15<00:00, 37.44it/s]
                                                            
Job alexxi19-ft-v1-nemo-ba-27407-v19-mkmlizer completed after 196.21s with status: succeeded
Stopping job with name alexxi19-ft-v1-nemo-ba-27407-v19-mkmlizer
Pipeline stage MKMLizer completed in 196.67s
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 alexxi19-ft-v1-nemo-ba-27407-v19
Waiting for inference service alexxi19-ft-v1-nemo-ba-27407-v19 to be ready
Failed to get response for submission nischaydnk-mistral24bas_35524_v1: HTTPConnectionPool(host='nischaydnk-mistral24bas-35524-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service alexxi19-ft-v1-nemo-ba-27407-v19 ready after 260.91110038757324s
Pipeline stage MKMLDeployer completed in 261.45s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4719903469085693s
Received healthy response to inference request in 1.603283405303955s
Received healthy response to inference request in 1.6979713439941406s
Received healthy response to inference request in 1.8687632083892822s
Received healthy response to inference request in 1.7542815208435059s
5 requests
0 failed requests
5th percentile: 1.6222209930419922
10th percentile: 1.6411585807800293
20th percentile: 1.6790337562561035
30th percentile: 1.7092333793640138
40th percentile: 1.7317574501037598
50th percentile: 1.7542815208435059
60th percentile: 1.8000741958618165
70th percentile: 1.845866870880127
80th percentile: 1.9894086360931398
90th percentile: 2.2306994915008547
95th percentile: 2.351344919204712
99th percentile: 2.4478612613677977
mean time: 1.8792579650878907
Pipeline stage StressChecker completed in 10.70s
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 0.63s
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 0.66s
Shutdown handler de-registered
alexxi19-ft-v1-nemo-ba_27407_v19 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 2780.41s
Shutdown handler de-registered
alexxi19-ft-v1-nemo-ba_27407_v19 status is now inactive due to auto deactivation removed underperforming models
alexxi19-ft-v1-nemo-ba_27407_v19 status is now torndown due to DeploymentManager action