riverise-lima-safe-sft

developer_uid: Riverise

submission_id: riverise-lima-safe-sft_v1

model_name: riverise-lima-safe-sft_v1

model_group: Riverise/lima_safe_sft

status: torndown

timestamp: 2025-01-06T12:55:58+00:00

num_battles: 13785

num_wins: 6516

celo_rating: 1240.24

family_friendly_score: 0.5986

family_friendly_standard_error: 0.006932215230357464

submission_type: basic

model_repo: Riverise/lima_safe_sft

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6177399466043761, 'latency_mean': 1.6187379682064056, 'latency_p50': 1.6166846752166748, 'latency_p90': 1.787411618232727}, {'batch_size': 3, 'throughput': 1.1351565389266296, 'latency_mean': 2.634934809207916, 'latency_p50': 2.609844207763672, 'latency_p90': 2.9358652114868162}, {'batch_size': 5, 'throughput': 1.3795876578481805, 'latency_mean': 3.6180020403862, 'latency_p50': 3.587460160255432, 'latency_p90': 4.123104572296143}, {'batch_size': 6, 'throughput': 1.4372038191029466, 'latency_mean': 4.158604706525803, 'latency_p50': 4.1489057540893555, 'latency_p90': 4.704988241195679}, {'batch_size': 8, 'throughput': 1.5099398555057733, 'latency_mean': 5.257755651473999, 'latency_p50': 5.1957844495773315, 'latency_p90': 5.912926864624023}, {'batch_size': 10, 'throughput': 1.555788115955983, 'latency_mean': 6.389099222421646, 'latency_p50': 6.395782470703125, 'latency_p90': 7.2054407596588135}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: riverise-lima-safe-sft_v1

is_internal_developer: False

language_model: Riverise/lima_safe_sft

model_size: 13B

ranking_group: single

throughput_3p7s: 1.39

us_pacific_date: 2025-01-06

win_ratio: 0.4726877040261153

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': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{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 riverise-lima-safe-sft-v1-mkmlizer
Waiting for job on riverise-lima-safe-sft-v1-mkmlizer to finish
riverise-lima-safe-sft-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
riverise-lima-safe-sft-v1-mkmlizer: ║     _____            __           __                                ║
riverise-lima-safe-sft-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
riverise-lima-safe-sft-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
riverise-lima-safe-sft-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
riverise-lima-safe-sft-v1-mkmlizer: ║       /___/                                                         ║
riverise-lima-safe-sft-v1-mkmlizer: ║                                                                     ║
riverise-lima-safe-sft-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
riverise-lima-safe-sft-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
riverise-lima-safe-sft-v1-mkmlizer: ║  https://mk1.ai                                                     ║
riverise-lima-safe-sft-v1-mkmlizer: ║                                                                     ║
riverise-lima-safe-sft-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
riverise-lima-safe-sft-v1-mkmlizer: ║  belonging to:                                                      ║
riverise-lima-safe-sft-v1-mkmlizer: ║                                                                     ║
riverise-lima-safe-sft-v1-mkmlizer: ║  Chai Research Corp.                                                ║
riverise-lima-safe-sft-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
riverise-lima-safe-sft-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
riverise-lima-safe-sft-v1-mkmlizer: ║                                                                     ║
riverise-lima-safe-sft-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
riverise-lima-safe-sft-v1-mkmlizer: Downloaded to shared memory in 100.178s
riverise-lima-safe-sft-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpg0pj2i22, device:0
riverise-lima-safe-sft-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
riverise-lima-safe-sft-v1-mkmlizer: quantized model in 42.748s
riverise-lima-safe-sft-v1-mkmlizer: Processed model Riverise/lima_safe_sft in 142.926s
riverise-lima-safe-sft-v1-mkmlizer: creating bucket guanaco-mkml-models
riverise-lima-safe-sft-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
riverise-lima-safe-sft-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/riverise-lima-safe-sft-v1
riverise-lima-safe-sft-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/riverise-lima-safe-sft-v1/config.json
riverise-lima-safe-sft-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/riverise-lima-safe-sft-v1/special_tokens_map.json
riverise-lima-safe-sft-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/riverise-lima-safe-sft-v1/tokenizer_config.json
riverise-lima-safe-sft-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/riverise-lima-safe-sft-v1/tokenizer.json
riverise-lima-safe-sft-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/riverise-lima-safe-sft-v1/flywheel_model.0.safetensors
riverise-lima-safe-sft-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 22.65it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 27.36it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:14, 24.04it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:11, 30.28it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:14, 22.67it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:16, 20.05it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:12, 25.69it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:12, 26.92it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:11, 27.69it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:12, 26.39it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:11, 26.60it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:13, 24.05it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:10, 29.07it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:09, 31.03it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:14, 20.64it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:11, 25.38it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:11, 25.10it/s]
Loading 0:  21%|██        | 77/363 [00:03<00:12, 23.30it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:09, 28.12it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:11, 24.95it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:09, 29.17it/s]
Loading 0:  26%|██▌       | 95/363 [00:03<00:10, 25.20it/s]
Loading 0:  28%|██▊       | 100/363 [00:03<00:08, 29.93it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:13, 19.92it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:10, 24.73it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:10, 22.97it/s]
Loading 0:  33%|███▎      | 118/363 [00:04<00:08, 27.75it/s]
Loading 0:  34%|███▎      | 122/363 [00:04<00:09, 24.54it/s]
Loading 0:  35%|███▍      | 127/363 [00:04<00:08, 28.34it/s]
Loading 0:  36%|███▌      | 131/363 [00:05<00:09, 24.84it/s]
Loading 0:  37%|███▋      | 136/363 [00:05<00:07, 29.04it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:07, 29.95it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:10, 21.58it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:10, 20.61it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:08, 25.01it/s]
Loading 0:  44%|████▎     | 158/363 [00:06<00:08, 22.89it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:07, 27.57it/s]
Loading 0:  46%|████▌     | 167/363 [00:06<00:07, 24.65it/s]
Loading 0:  47%|████▋     | 172/363 [00:06<00:06, 29.24it/s]
Loading 0:  48%|████▊     | 176/363 [00:06<00:07, 24.69it/s]
Loading 0:  50%|████▉     | 181/363 [00:07<00:06, 28.68it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:09, 18.99it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 23.68it/s]
Loading 0:  53%|█████▎    | 194/363 [00:07<00:07, 22.08it/s]
Loading 0:  55%|█████▌    | 201/363 [00:07<00:05, 28.09it/s]
Loading 0:  56%|█████▋    | 205/363 [00:08<00:05, 26.66it/s]
Loading 0:  58%|█████▊    | 210/363 [00:08<00:05, 28.87it/s]
Loading 0:  59%|█████▉    | 214/363 [00:08<00:05, 27.40it/s]
Loading 0:  60%|██████    | 218/363 [00:08<00:05, 27.05it/s]
Loading 0:  61%|██████    | 222/363 [00:08<00:04, 29.22it/s]
Loading 0:  62%|██████▏   | 226/363 [00:09<00:06, 20.98it/s]
Loading 0:  63%|██████▎   | 230/363 [00:09<00:06, 20.46it/s]
Loading 0:  65%|██████▌   | 237/363 [00:09<00:04, 26.99it/s]
Loading 0:  66%|██████▋   | 241/363 [00:09<00:04, 26.43it/s]
Loading 0:  68%|██████▊   | 246/363 [00:09<00:04, 28.85it/s]
Loading 0:  69%|██████▉   | 250/363 [00:09<00:04, 27.60it/s]
Loading 0:  70%|██████▉   | 253/363 [00:09<00:03, 27.80it/s]
Loading 0:  71%|███████   | 257/363 [00:10<00:04, 24.86it/s]
Loading 0:  72%|███████▏  | 263/363 [00:10<00:04, 24.86it/s]
Loading 0:  73%|███████▎  | 266/363 [00:10<00:04, 21.61it/s]
Loading 0:  75%|███████▌  | 273/363 [00:10<00:03, 27.91it/s]
Loading 0:  76%|███████▌  | 276/363 [00:10<00:03, 25.66it/s]
Loading 0:  77%|███████▋  | 280/363 [00:10<00:02, 28.30it/s]
Loading 0:  78%|███████▊  | 284/363 [00:11<00:03, 24.91it/s]
Loading 0:  80%|███████▉  | 289/363 [00:11<00:02, 29.92it/s]
Loading 0:  81%|████████  | 293/363 [00:11<00:02, 25.92it/s]
Loading 0:  82%|████████▏ | 298/363 [00:11<00:02, 30.67it/s]
Loading 0:  83%|████████▎ | 303/363 [00:11<00:01, 31.64it/s]
Loading 0:  85%|████████▍ | 307/363 [00:12<00:02, 22.64it/s]
Loading 0:  86%|████████▌ | 311/363 [00:12<00:02, 21.71it/s]
Loading 0:  87%|████████▋ | 316/363 [00:12<00:01, 26.55it/s]
Loading 0:  88%|████████▊ | 320/363 [00:12<00:01, 24.25it/s]
Loading 0:  90%|████████▉ | 325/363 [00:12<00:01, 29.04it/s]
Loading 0:  91%|█████████ | 329/363 [00:12<00:01, 25.51it/s]
Loading 0:  92%|█████████▏| 334/363 [00:12<00:00, 30.33it/s]
Loading 0:  93%|█████████▎| 338/363 [00:13<00:00, 26.39it/s]
Loading 0:  95%|█████████▍| 344/363 [00:20<00:08,  2.18it/s]
Loading 0:  96%|█████████▌| 348/363 [00:20<00:05,  2.83it/s]
Loading 0:  97%|█████████▋| 353/363 [00:20<00:02,  4.00it/s]
Loading 0:  98%|█████████▊| 357/363 [00:20<00:01,  5.06it/s]
Loading 0: 100%|█████████▉| 362/363 [00:20<00:00,  7.10it/s]
                                                            
Job riverise-lima-safe-sft-v1-mkmlizer completed after 167.23s with status: succeeded
Stopping job with name riverise-lima-safe-sft-v1-mkmlizer
Pipeline stage MKMLizer completed in 168.06s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service riverise-lima-safe-sft-v1
Waiting for inference service riverise-lima-safe-sft-v1 to be ready
Inference service riverise-lima-safe-sft-v1 ready after 351.67950558662415s
Pipeline stage MKMLDeployer completed in 352.23s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.036835193634033s
Received healthy response to inference request in 1.5468289852142334s
Received healthy response to inference request in 1.798426866531372s
Received healthy response to inference request in 2.2460505962371826s
Received healthy response to inference request in 1.9768400192260742s
5 requests
0 failed requests
5th percentile: 1.597148561477661
10th percentile: 1.647468137741089
20th percentile: 1.7481072902679444
30th percentile: 1.8341094970703125
40th percentile: 1.9054747581481934
50th percentile: 1.9768400192260742
60th percentile: 2.0008380889892576
70th percentile: 2.0248361587524415
80th percentile: 2.078678274154663
90th percentile: 2.162364435195923
95th percentile: 2.204207515716553
99th percentile: 2.2376819801330567
mean time: 1.920996332168579
Pipeline stage StressChecker completed in 10.86s
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 0.70s
Shutdown handler de-registered
riverise-lima-safe-sft_v1 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 3024.29s
Shutdown handler de-registered
riverise-lima-safe-sft_v1 status is now inactive due to auto deactivation removed underperforming models
riverise-lima-safe-sft_v1 status is now torndown due to DeploymentManager action
riverise-lima-safe-sft_v1 status is now torndown due to DeploymentManager action
riverise-lima-safe-sft_v1 status is now torndown due to DeploymentManager action