alexxi19-ft-v1-nemo-ba_27407

developer_uid: leosheng

submission_id: alexxi19-ft-v1-nemo-ba_27407_v24

model_name: alexxi19-ft-v1-nemo-ba_27407_v24

model_group: alexxi19/ft-v1-nemo-base

status: inactive

timestamp: 2025-03-13T04:39:11+00:00

num_battles: 6811

num_wins: 3456

celo_rating: 1264.65

family_friendly_score: 0.5512

family_friendly_standard_error: 0.007033897354951947

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: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6061885585383996, 'latency_mean': 1.6495784294605256, 'latency_p50': 1.6509193181991577, 'latency_p90': 1.8157488822937011}, {'batch_size': 3, 'throughput': 1.1259902173575693, 'latency_mean': 2.6524600267410277, 'latency_p50': 2.631512999534607, 'latency_p90': 2.892352509498596}, {'batch_size': 5, 'throughput': 1.355789291686867, 'latency_mean': 3.6717112016677858, 'latency_p50': 3.6795142889022827, 'latency_p90': 4.077416276931762}, {'batch_size': 6, 'throughput': 1.4270923578091366, 'latency_mean': 4.188997856378555, 'latency_p50': 4.1719865798950195, 'latency_p90': 4.67370114326477}, {'batch_size': 8, 'throughput': 1.5015269662304678, 'latency_mean': 5.294022046327591, 'latency_p50': 5.266498446464539, 'latency_p90': 5.9560990810394285}, {'batch_size': 10, 'throughput': 1.5327053794381158, 'latency_mean': 6.460347524881363, 'latency_p50': 6.4961079359054565, 'latency_p90': 7.318888568878174}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: alexxi19-ft-v1-nemo-ba_27407_v24

is_internal_developer: False

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

model_size: 13B

ranking_group: single

throughput_3p7s: 1.37

us_pacific_date: 2025-03-12

win_ratio: 0.5074144765819997

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-v1-nemo-ba-27407-v24-mkmlizer
Waiting for job on alexxi19-ft-v1-nemo-ba-27407-v24-mkmlizer to finish
alexxi19-ft-v1-nemo-ba-27407-v24-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexxi19-ft-v1-nemo-ba-27407-v24-mkmlizer: ║     _____            __           __                                ║
alexxi19-ft-v1-nemo-ba-27407-v24-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
alexxi19-ft-v1-nemo-ba-27407-v24-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
alexxi19-ft-v1-nemo-ba-27407-v24-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
alexxi19-ft-v1-nemo-ba-27407-v24-mkmlizer: ║       /___/                                                         ║
alexxi19-ft-v1-nemo-ba-27407-v24-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-ba-27407-v24-mkmlizer: ║  Version: 0.12.8                                                    ║
alexxi19-ft-v1-nemo-ba-27407-v24-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
alexxi19-ft-v1-nemo-ba-27407-v24-mkmlizer: ║  https://mk1.ai                                                     ║
alexxi19-ft-v1-nemo-ba-27407-v24-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-ba-27407-v24-mkmlizer: ║  The license key for the current software has been verified as      ║
alexxi19-ft-v1-nemo-ba-27407-v24-mkmlizer: ║  belonging to:                                                      ║
alexxi19-ft-v1-nemo-ba-27407-v24-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-ba-27407-v24-mkmlizer: ║  Chai Research Corp.                                                ║
alexxi19-ft-v1-nemo-ba-27407-v24-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
alexxi19-ft-v1-nemo-ba-27407-v24-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
alexxi19-ft-v1-nemo-ba-27407-v24-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-ba-27407-v24-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission jellywibble-enzo-mafia-enemy_v12: HTTPConnectionPool(host='jellywibble-enzo-mafia-enemy-v12-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
alexxi19-ft-v1-nemo-ba-27407-v24-mkmlizer: Downloaded to shared memory in 141.933s
alexxi19-ft-v1-nemo-ba-27407-v24-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp5vw_zgt9, device:0
alexxi19-ft-v1-nemo-ba-27407-v24-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alexxi19-ft-v1-nemo-ba-27407-v24-mkmlizer: quantized model in 36.207s
alexxi19-ft-v1-nemo-ba-27407-v24-mkmlizer: Processed model alexxi19/ft-v1-nemo-base-merge-v1 in 178.141s
alexxi19-ft-v1-nemo-ba-27407-v24-mkmlizer: creating bucket guanaco-mkml-models
alexxi19-ft-v1-nemo-ba-27407-v24-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexxi19-ft-v1-nemo-ba-27407-v24-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v24
alexxi19-ft-v1-nemo-ba-27407-v24-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v24/config.json
alexxi19-ft-v1-nemo-ba-27407-v24-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v24/special_tokens_map.json
alexxi19-ft-v1-nemo-ba-27407-v24-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v24/tokenizer_config.json
alexxi19-ft-v1-nemo-ba-27407-v24-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v24/tokenizer.json
alexxi19-ft-v1-nemo-ba-27407-v24-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v24/flywheel_model.0.safetensors
alexxi19-ft-v1-nemo-ba-27407-v24-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:29,  3.07s/it]
Loading 0:   1%|          | 3/363 [00:06<11:03,  1.84s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:05,  1.45it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:20,  4.35it/s]
Loading 0:   5%|▍         | 18/363 [00:06<00:51,  6.70it/s]
Loading 0:   6%|▋         | 23/363 [00:06<00:34,  9.85it/s]
Loading 0:   8%|▊         | 29/363 [00:06<00:23, 14.18it/s]
Loading 0:   9%|▉         | 34/363 [00:07<00:19, 16.73it/s]
Loading 0:  11%|█▏        | 41/363 [00:07<00:13, 23.22it/s]
Loading 0:  13%|█▎        | 47/363 [00:07<00:11, 27.29it/s]
Loading 0:  14%|█▍        | 52/363 [00:07<00:11, 27.38it/s]
Loading 0:  16%|█▋        | 59/363 [00:07<00:09, 33.54it/s]
Loading 0:  18%|█▊        | 64/363 [00:07<00:08, 36.35it/s]
Loading 0:  19%|█▉        | 69/363 [00:07<00:09, 30.73it/s]
Loading 0:  21%|██        | 77/363 [00:08<00:07, 39.69it/s]
Loading 0:  23%|██▎       | 82/363 [00:08<00:07, 37.16it/s]
Loading 0:  24%|██▍       | 87/363 [00:08<00:07, 35.22it/s]
Loading 0:  26%|██▌       | 95/363 [00:08<00:06, 43.86it/s]
Loading 0:  28%|██▊       | 100/363 [00:08<00:06, 39.29it/s]
Loading 0:  29%|██▉       | 105/363 [00:08<00:07, 36.27it/s]
Loading 0:  31%|███       | 113/363 [00:09<00:06, 38.79it/s]
Loading 0:  33%|███▎      | 119/363 [00:09<00:06, 39.18it/s]
Loading 0:  34%|███▍      | 124/363 [00:09<00:06, 39.60it/s]
Loading 0:  36%|███▌      | 130/363 [00:09<00:05, 39.02it/s]
Loading 0:  37%|███▋      | 134/363 [00:09<00:05, 39.07it/s]
Loading 0:  39%|███▊      | 140/363 [00:09<00:05, 42.77it/s]
Loading 0:  40%|███▉      | 145/363 [00:09<00:05, 38.51it/s]
Loading 0:  41%|████      | 149/363 [00:09<00:05, 38.72it/s]
Loading 0:  42%|████▏     | 153/363 [00:10<00:05, 38.33it/s]
Loading 0:  44%|████▎     | 158/363 [00:10<00:05, 39.71it/s]
Loading 0:  45%|████▍     | 163/363 [00:10<00:05, 34.86it/s]
Loading 0:  46%|████▋     | 168/363 [00:10<00:05, 33.49it/s]
Loading 0:  48%|████▊     | 176/363 [00:10<00:05, 36.47it/s]
Loading 0:  50%|█████     | 182/363 [00:10<00:04, 37.97it/s]
Loading 0:  51%|█████     | 186/363 [00:10<00:04, 37.14it/s]
Loading 0:  53%|█████▎    | 193/363 [00:11<00:04, 39.07it/s]
Loading 0:  54%|█████▍    | 197/363 [00:11<00:04, 39.18it/s]
Loading 0:  56%|█████▌    | 203/363 [00:11<00:03, 42.63it/s]
Loading 0:  57%|█████▋    | 208/363 [00:11<00:03, 39.34it/s]
Loading 0:  59%|█████▊    | 213/363 [00:11<00:04, 35.93it/s]
Loading 0:  61%|██████    | 220/363 [00:11<00:03, 43.24it/s]
Loading 0:  62%|██████▏   | 225/363 [00:11<00:03, 38.05it/s]
Loading 0:  63%|██████▎   | 230/363 [00:12<00:03, 40.48it/s]
Loading 0:  65%|██████▌   | 236/363 [00:12<00:03, 41.05it/s]
Loading 0:  66%|██████▋   | 241/363 [00:12<00:03, 35.32it/s]
Loading 0:  68%|██████▊   | 247/363 [00:12<00:02, 40.63it/s]
Loading 0:  69%|██████▉   | 252/363 [00:12<00:02, 42.17it/s]
Loading 0:  71%|███████   | 257/363 [00:12<00:02, 38.11it/s]
Loading 0:  72%|███████▏  | 263/363 [00:12<00:02, 39.43it/s]
Loading 0:  74%|███████▍  | 268/363 [00:13<00:02, 39.98it/s]
Loading 0:  75%|███████▌  | 273/363 [00:13<00:02, 38.18it/s]
Loading 0:  76%|███████▋  | 277/363 [00:13<00:02, 37.14it/s]
Loading 0:  78%|███████▊  | 284/363 [00:13<00:01, 43.55it/s]
Loading 0:  80%|███████▉  | 289/363 [00:13<00:01, 38.54it/s]
Loading 0:  81%|████████  | 294/363 [00:13<00:01, 35.93it/s]
Loading 0:  83%|████████▎ | 302/363 [00:13<00:01, 37.44it/s]
Loading 0:  85%|████████▍ | 307/363 [00:14<00:01, 40.03it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:01, 36.05it/s]
Loading 0:  88%|████████▊ | 319/363 [00:14<00:01, 38.13it/s]
Loading 0:  89%|████████▉ | 323/363 [00:14<00:01, 38.27it/s]
Loading 0:  90%|█████████ | 328/363 [00:14<00:00, 40.17it/s]
Loading 0:  92%|█████████▏| 333/363 [00:14<00:00, 34.61it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:00, 37.76it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:00, 39.76it/s]
Loading 0:  96%|█████████▌| 349/363 [00:15<00:00, 30.75it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 37.09it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 39.11it/s]
                                                            
Job alexxi19-ft-v1-nemo-ba-27407-v24-mkmlizer completed after 206.94s with status: succeeded
Stopping job with name alexxi19-ft-v1-nemo-ba-27407-v24-mkmlizer
Pipeline stage MKMLizer completed in 207.41s
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-v24
Waiting for inference service alexxi19-ft-v1-nemo-ba-27407-v24 to be ready
Failed to get response for submission jellywibble-enzo-mafia-enemy_v12: HTTPConnectionPool(host='jellywibble-enzo-mafia-enemy-v12-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service alexxi19-ft-v1-nemo-ba-27407-v24 ready after 90.71271562576294s
Pipeline stage MKMLDeployer completed in 91.25s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5366928577423096s
Received healthy response to inference request in 1.6856467723846436s
Received healthy response to inference request in 1.5117859840393066s
Received healthy response to inference request in 1.6778452396392822s
Received healthy response to inference request in 1.763495922088623s
5 requests
0 failed requests
5th percentile: 1.5449978351593017
10th percentile: 1.578209686279297
20th percentile: 1.6446333885192872
30th percentile: 1.6794055461883546
40th percentile: 1.682526159286499
50th percentile: 1.6856467723846436
60th percentile: 1.7167864322662354
70th percentile: 1.7479260921478272
80th percentile: 1.9181353092193605
90th percentile: 2.227414083480835
95th percentile: 2.382053470611572
99th percentile: 2.505764980316162
mean time: 1.835093355178833
Pipeline stage StressChecker completed in 10.43s
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 0.66s
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 0.73s
Shutdown handler de-registered
alexxi19-ft-v1-nemo-ba_27407_v24 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 alexxi19-ft-v1-nemo-ba-27407-v24-profiler
Waiting for inference service alexxi19-ft-v1-nemo-ba-27407-v24-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 2764.18s
Shutdown handler de-registered
alexxi19-ft-v1-nemo-ba_27407_v24 status is now inactive due to auto deactivation removed underperforming models