alexxi19-ft-v1-nemo-ba_27407

developer_uid: leosheng

submission_id: alexxi19-ft-v1-nemo-ba_27407_v25

model_name: alexxi19-ft-v1-nemo-ba_27407_v25

model_group: alexxi19/ft-v1-nemo-base

status: inactive

timestamp: 2025-03-13T07:22:37+00:00

num_battles: 10187

num_wins: 4893

celo_rating: 1267.77

family_friendly_score: 0.5578000000000001

family_friendly_standard_error: 0.007023662292565041

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': 0.6038899348112862, 'latency_mean': 1.655832017660141, 'latency_p50': 1.6538258790969849, 'latency_p90': 1.813031506538391}, {'batch_size': 3, 'throughput': 1.0992014614179129, 'latency_mean': 2.7213345754146574, 'latency_p50': 2.6976760625839233, 'latency_p90': 3.025252366065979}, {'batch_size': 5, 'throughput': 1.3102526635839464, 'latency_mean': 3.800894559621811, 'latency_p50': 3.7949371337890625, 'latency_p90': 4.273691082000732}, {'batch_size': 6, 'throughput': 1.3706598191190886, 'latency_mean': 4.353047095537185, 'latency_p50': 4.365954041481018, 'latency_p90': 4.843268465995789}, {'batch_size': 8, 'throughput': 1.4423957192357728, 'latency_mean': 5.505267609357833, 'latency_p50': 5.517248511314392, 'latency_p90': 6.182631087303162}, {'batch_size': 10, 'throughput': 1.47586746118318, 'latency_mean': 6.715209053754807, 'latency_p50': 6.722273468971252, 'latency_p90': 7.5242973327636715}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: alexxi19-ft-v1-nemo-ba_27407_v25

is_internal_developer: False

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

model_size: 13B

ranking_group: single

throughput_3p7s: 1.3

us_pacific_date: 2025-03-13

win_ratio: 0.4803180524197507

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-v25-mkmlizer
Waiting for job on alexxi19-ft-v1-nemo-ba-27407-v25-mkmlizer to finish
alexxi19-ft-v1-nemo-ba-27407-v25-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexxi19-ft-v1-nemo-ba-27407-v25-mkmlizer: ║     _____            __           __                                ║
alexxi19-ft-v1-nemo-ba-27407-v25-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
alexxi19-ft-v1-nemo-ba-27407-v25-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
alexxi19-ft-v1-nemo-ba-27407-v25-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
alexxi19-ft-v1-nemo-ba-27407-v25-mkmlizer: ║       /___/                                                         ║
alexxi19-ft-v1-nemo-ba-27407-v25-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-ba-27407-v25-mkmlizer: ║  Version: 0.12.8                                                    ║
alexxi19-ft-v1-nemo-ba-27407-v25-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
alexxi19-ft-v1-nemo-ba-27407-v25-mkmlizer: ║  https://mk1.ai                                                     ║
alexxi19-ft-v1-nemo-ba-27407-v25-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-ba-27407-v25-mkmlizer: ║  The license key for the current software has been verified as      ║
alexxi19-ft-v1-nemo-ba-27407-v25-mkmlizer: ║  belonging to:                                                      ║
alexxi19-ft-v1-nemo-ba-27407-v25-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-ba-27407-v25-mkmlizer: ║  Chai Research Corp.                                                ║
alexxi19-ft-v1-nemo-ba-27407-v25-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
alexxi19-ft-v1-nemo-ba-27407-v25-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
alexxi19-ft-v1-nemo-ba-27407-v25-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-ba-27407-v25-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alexxi19-ft-v1-nemo-ba-27407-v25-mkmlizer: Downloaded to shared memory in 132.546s
alexxi19-ft-v1-nemo-ba-27407-v25-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp879mtwen, device:0
alexxi19-ft-v1-nemo-ba-27407-v25-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alexxi19-ft-v1-nemo-ba-27407-v25-mkmlizer: quantized model in 37.162s
alexxi19-ft-v1-nemo-ba-27407-v25-mkmlizer: Processed model alexxi19/ft-v1-nemo-base-merge-v1 in 169.708s
alexxi19-ft-v1-nemo-ba-27407-v25-mkmlizer: creating bucket guanaco-mkml-models
alexxi19-ft-v1-nemo-ba-27407-v25-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexxi19-ft-v1-nemo-ba-27407-v25-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v25
alexxi19-ft-v1-nemo-ba-27407-v25-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v25/config.json
alexxi19-ft-v1-nemo-ba-27407-v25-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v25/special_tokens_map.json
alexxi19-ft-v1-nemo-ba-27407-v25-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v25/tokenizer_config.json
alexxi19-ft-v1-nemo-ba-27407-v25-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v25/tokenizer.json
alexxi19-ft-v1-nemo-ba-27407-v25-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-ba-27407-v25/flywheel_model.0.safetensors
alexxi19-ft-v1-nemo-ba-27407-v25-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:37,  3.09s/it]
Loading 0:   1%|          | 3/363 [00:06<11:08,  1.86s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:08,  1.44it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:21,  4.30it/s]
Loading 0:   5%|▍         | 18/363 [00:06<00:52,  6.60it/s]
Loading 0:   6%|▋         | 23/363 [00:06<00:35,  9.69it/s]
Loading 0:   8%|▊         | 29/363 [00:06<00:24, 13.87it/s]
Loading 0:   9%|▉         | 33/363 [00:07<00:21, 15.29it/s]
Loading 0:  11%|█▏        | 41/363 [00:07<00:13, 23.15it/s]
Loading 0:  13%|█▎        | 47/363 [00:07<00:11, 27.04it/s]
Loading 0:  14%|█▍        | 52/363 [00:07<00:11, 26.50it/s]
Loading 0:  16%|█▋        | 59/363 [00:07<00:09, 32.96it/s]
Loading 0:  18%|█▊        | 65/363 [00:07<00:08, 35.39it/s]
Loading 0:  19%|█▉        | 70/363 [00:08<00:09, 31.33it/s]
Loading 0:  21%|██        | 76/363 [00:08<00:07, 36.68it/s]
Loading 0:  22%|██▏       | 81/363 [00:08<00:08, 32.92it/s]
Loading 0:  23%|██▎       | 85/363 [00:08<00:08, 33.27it/s]
Loading 0:  25%|██▍       | 89/363 [00:08<00:07, 34.45it/s]
Loading 0:  26%|██▌       | 95/363 [00:08<00:06, 39.56it/s]
Loading 0:  28%|██▊       | 100/363 [00:08<00:07, 36.11it/s]
Loading 0:  29%|██▊       | 104/363 [00:08<00:07, 36.16it/s]
Loading 0:  30%|███       | 110/363 [00:09<00:06, 38.02it/s]
Loading 0:  31%|███▏      | 114/363 [00:09<00:07, 31.27it/s]
Loading 0:  33%|███▎      | 121/363 [00:09<00:06, 39.33it/s]
Loading 0:  35%|███▍      | 126/363 [00:09<00:05, 40.59it/s]
Loading 0:  36%|███▌      | 131/363 [00:09<00:06, 36.27it/s]
Loading 0:  38%|███▊      | 137/363 [00:09<00:06, 37.36it/s]
Loading 0:  39%|███▉      | 141/363 [00:09<00:06, 36.09it/s]
Loading 0:  40%|████      | 146/363 [00:10<00:06, 35.42it/s]
Loading 0:  41%|████▏     | 150/363 [00:10<00:06, 34.67it/s]
Loading 0:  43%|████▎     | 157/363 [00:10<00:05, 40.69it/s]
Loading 0:  45%|████▍     | 162/363 [00:10<00:05, 34.68it/s]
Loading 0:  46%|████▌     | 166/363 [00:10<00:05, 34.93it/s]
Loading 0:  47%|████▋     | 171/363 [00:10<00:05, 37.66it/s]
Loading 0:  48%|████▊     | 176/363 [00:11<00:05, 33.20it/s]
Loading 0:  50%|█████     | 182/363 [00:11<00:05, 35.38it/s]
Loading 0:  51%|█████     | 186/363 [00:11<00:05, 34.72it/s]
Loading 0:  53%|█████▎    | 193/363 [00:11<00:04, 36.54it/s]
Loading 0:  54%|█████▍    | 197/363 [00:11<00:04, 37.13it/s]
Loading 0:  56%|█████▌    | 203/363 [00:11<00:03, 40.58it/s]
Loading 0:  57%|█████▋    | 208/363 [00:11<00:04, 35.09it/s]
Loading 0:  58%|█████▊    | 212/363 [00:11<00:04, 35.35it/s]
Loading 0:  60%|██████    | 218/363 [00:12<00:03, 37.42it/s]
Loading 0:  61%|██████    | 222/363 [00:12<00:04, 30.84it/s]
Loading 0:  63%|██████▎   | 229/363 [00:12<00:03, 38.47it/s]
Loading 0:  64%|██████▍   | 234/363 [00:12<00:03, 40.05it/s]
Loading 0:  66%|██████▌   | 239/363 [00:12<00:03, 35.87it/s]
Loading 0:  67%|██████▋   | 245/363 [00:12<00:03, 36.66it/s]
Loading 0:  69%|██████▊   | 249/363 [00:13<00:03, 33.64it/s]
Loading 0:  71%|███████   | 256/363 [00:13<00:03, 34.96it/s]
Loading 0:  72%|███████▏  | 260/363 [00:13<00:02, 35.87it/s]
Loading 0:  73%|███████▎  | 265/363 [00:13<00:02, 38.97it/s]
Loading 0:  74%|███████▍  | 270/363 [00:13<00:02, 34.57it/s]
Loading 0:  76%|███████▌  | 275/363 [00:13<00:02, 37.20it/s]
Loading 0:  77%|███████▋  | 281/363 [00:13<00:02, 38.51it/s]
Loading 0:  79%|███████▊  | 285/363 [00:14<00:02, 31.44it/s]
Loading 0:  81%|████████  | 293/363 [00:14<00:01, 40.01it/s]
Loading 0:  82%|████████▏ | 299/363 [00:14<00:01, 40.47it/s]
Loading 0:  84%|████████▎ | 304/363 [00:14<00:01, 34.24it/s]
Loading 0:  86%|████████▌ | 311/363 [00:14<00:01, 39.85it/s]
Loading 0:  87%|████████▋ | 317/363 [00:14<00:01, 40.63it/s]
Loading 0:  89%|████████▊ | 322/363 [00:14<00:01, 35.09it/s]
Loading 0:  91%|█████████ | 329/363 [00:15<00:00, 40.70it/s]
Loading 0:  92%|█████████▏| 334/363 [00:15<00:00, 37.87it/s]
Loading 0:  93%|█████████▎| 339/363 [00:15<00:00, 34.23it/s]
Loading 0:  96%|█████████▌| 347/363 [00:15<00:00, 41.99it/s]
Loading 0:  97%|█████████▋| 352/363 [00:15<00:00, 38.25it/s]
Loading 0:  98%|█████████▊| 357/363 [00:15<00:00, 33.02it/s]
                                                            
Job alexxi19-ft-v1-nemo-ba-27407-v25-mkmlizer completed after 195.62s with status: succeeded
Stopping job with name alexxi19-ft-v1-nemo-ba-27407-v25-mkmlizer
Pipeline stage MKMLizer completed in 196.11s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.20s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service alexxi19-ft-v1-nemo-ba-27407-v25
Waiting for inference service alexxi19-ft-v1-nemo-ba-27407-v25 to be ready
Inference service alexxi19-ft-v1-nemo-ba-27407-v25 ready after 90.3273286819458s
Pipeline stage MKMLDeployer completed in 90.87s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5692005157470703s
Received healthy response to inference request in 1.6500258445739746s
Received healthy response to inference request in 1.6237726211547852s
Received healthy response to inference request in 1.5144519805908203s
Received healthy response to inference request in 1.654548168182373s
5 requests
0 failed requests
5th percentile: 1.5363161087036132
10th percentile: 1.5581802368164062
20th percentile: 1.6019084930419922
30th percentile: 1.629023265838623
40th percentile: 1.639524555206299
50th percentile: 1.6500258445739746
60th percentile: 1.651834774017334
70th percentile: 1.6536437034606934
80th percentile: 1.8374786376953127
90th percentile: 2.2033395767211914
95th percentile: 2.386270046234131
99th percentile: 2.5326144218444826
mean time: 1.8023998260498046
Pipeline stage StressChecker completed in 10.42s
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 0.69s
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 0.69s
Shutdown handler de-registered
alexxi19-ft-v1-nemo-ba_27407_v25 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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4313.50s
Shutdown handler de-registered
alexxi19-ft-v1-nemo-ba_27407_v25 status is now inactive due to auto deactivation removed underperforming models