chaiml-mistral-nemo-simp_2479

developer_uid: azuruce

submission_id: chaiml-mistral-nemo-simp_2479_v2

model_name: chaiml-mistral-nemo-simp_2479_v2

model_group: ChaiML/mistral_nemo_simp

status: inactive

timestamp: 2024-12-17T20:27:36+00:00

num_battles: 10558

num_wins: 4900

celo_rating: 1236.07

family_friendly_score: 0.5842

family_friendly_standard_error: 0.006970084074098389

submission_type: basic

model_repo: ChaiML/mistral_nemo_simpo_baseline_albert_20241213_v1-checkpoint-624

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.634901918082156, 'latency_mean': 1.5749645113945008, 'latency_p50': 1.5707333087921143, 'latency_p90': 1.7344859838485718}, {'batch_size': 3, 'throughput': 1.269251527736036, 'latency_mean': 2.3537900757789614, 'latency_p50': 2.335339903831482, 'latency_p90': 2.6307311058044434}, {'batch_size': 5, 'throughput': 1.596051999068063, 'latency_mean': 3.1229457628726958, 'latency_p50': 3.1249139308929443, 'latency_p90': 3.4345160722732544}, {'batch_size': 6, 'throughput': 1.7069496510808675, 'latency_mean': 3.485679988861084, 'latency_p50': 3.458243250846863, 'latency_p90': 3.93124406337738}, {'batch_size': 8, 'throughput': 1.8645675789153648, 'latency_mean': 4.253226809501648, 'latency_p50': 4.2936931848526, 'latency_p90': 4.8041398286819454}, {'batch_size': 10, 'throughput': 1.9376127135988406, 'latency_mean': 5.1224603950977325, 'latency_p50': 5.142012596130371, 'latency_p90': 5.794326615333557}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-mistral-nemo-simp_2479_v2

is_internal_developer: True

language_model: ChaiML/mistral_nemo_simpo_baseline_albert_20241213_v1-checkpoint-624

model_size: 13B

ranking_group: single

throughput_3p7s: 1.77

us_pacific_date: 2024-12-17

win_ratio: 0.4641030498200417

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '####', 'Bot:', 'User:', 'You:', '<|im_end|>', '<|eot_id|>'], 'max_input_tokens': 1024, 'best_of': 4, 'max_output_tokens': 64}

formatter: {'memory_template': '', 'prompt_template': '', '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 chaiml-mistral-nemo-simp-2479-v2-mkmlizer
Waiting for job on chaiml-mistral-nemo-simp-2479-v2-mkmlizer to finish
Retrying (%r) after connection broken by '%r': %s
chaiml-mistral-nemo-simp-2479-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-nemo-simp-2479-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-mistral-nemo-simp-2479-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-mistral-nemo-simp-2479-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-mistral-nemo-simp-2479-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-mistral-nemo-simp-2479-v2-mkmlizer: ║       /___/                                                         ║
chaiml-mistral-nemo-simp-2479-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-simp-2479-v2-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-mistral-nemo-simp-2479-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-mistral-nemo-simp-2479-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral-nemo-simp-2479-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-simp-2479-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral-nemo-simp-2479-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral-nemo-simp-2479-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-simp-2479-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral-nemo-simp-2479-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral-nemo-simp-2479-v2-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-mistral-nemo-simp-2479-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-simp-2479-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral-nemo-simp-2479-v2-mkmlizer: Downloaded to shared memory in 34.459s
chaiml-mistral-nemo-simp-2479-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpysljki8d, device:0
chaiml-mistral-nemo-simp-2479-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral-nemo-simp-2479-v2-mkmlizer: quantized model in 36.366s
chaiml-mistral-nemo-simp-2479-v2-mkmlizer: Processed model ChaiML/mistral_nemo_simpo_baseline_albert_20241213_v1-checkpoint-624 in 70.825s
chaiml-mistral-nemo-simp-2479-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-nemo-simp-2479-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-nemo-simp-2479-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-nemo-simp-2479-v2
chaiml-mistral-nemo-simp-2479-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-simp-2479-v2/config.json
chaiml-mistral-nemo-simp-2479-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral-nemo-simp-2479-v2/special_tokens_map.json
chaiml-mistral-nemo-simp-2479-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-simp-2479-v2/tokenizer_config.json
chaiml-mistral-nemo-simp-2479-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral-nemo-simp-2479-v2/tokenizer.json
chaiml-mistral-nemo-simp-2479-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-nemo-simp-2479-v2/flywheel_model.0.safetensors
chaiml-mistral-nemo-simp-2479-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 27.97it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 49.53it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 47.38it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:06, 48.40it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 50.96it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 48.45it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:06, 46.19it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 49.98it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 45.60it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:06, 46.23it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:10, 29.70it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:08, 35.96it/s]
Loading 0:  21%|██        | 77/363 [00:01<00:07, 37.92it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:08, 34.06it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:06, 42.16it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:06, 40.69it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:06, 39.18it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:06, 41.55it/s]
Loading 0:  31%|███       | 113/363 [00:02<00:06, 41.57it/s]
Loading 0:  33%|███▎      | 118/363 [00:02<00:05, 41.11it/s]
Loading 0:  35%|███▍      | 126/363 [00:02<00:04, 48.50it/s]
Loading 0:  36%|███▋      | 132/363 [00:03<00:04, 46.31it/s]
Loading 0:  38%|███▊      | 137/363 [00:03<00:05, 45.16it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 33.93it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 34.88it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 34.40it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:05, 40.67it/s]
Loading 0:  45%|████▍     | 163/363 [00:03<00:05, 39.95it/s]
Loading 0:  46%|████▋     | 168/363 [00:04<00:05, 38.88it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:04, 43.93it/s]
Loading 0:  50%|████▉     | 180/363 [00:04<00:04, 44.47it/s]
Loading 0:  51%|█████     | 185/363 [00:04<00:04, 37.22it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 45.24it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:03, 42.81it/s]
Loading 0:  56%|█████▌    | 204/363 [00:04<00:03, 40.58it/s]
Loading 0:  58%|█████▊    | 211/363 [00:05<00:03, 45.68it/s]
Loading 0:  60%|█████▉    | 217/363 [00:05<00:03, 43.55it/s]
Loading 0:  61%|██████    | 222/363 [00:05<00:03, 44.85it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:04, 30.74it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:04, 30.67it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:03, 37.66it/s]
Loading 0:  67%|██████▋   | 244/363 [00:06<00:03, 38.26it/s]
Loading 0:  69%|██████▊   | 249/363 [00:06<00:02, 38.37it/s]
Loading 0:  70%|███████   | 255/363 [00:06<00:02, 43.24it/s]
Loading 0:  72%|███████▏  | 260/363 [00:06<00:02, 41.54it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 43.34it/s]
Loading 0:  75%|███████▍  | 271/363 [00:06<00:02, 42.56it/s]
Loading 0:  76%|███████▌  | 276/363 [00:06<00:02, 41.98it/s]
Loading 0:  78%|███████▊  | 283/363 [00:06<00:01, 47.65it/s]
Loading 0:  80%|███████▉  | 289/363 [00:07<00:01, 45.96it/s]
Loading 0:  81%|████████  | 294/363 [00:07<00:01, 43.41it/s]
Loading 0:  83%|████████▎ | 300/363 [00:07<00:01, 47.44it/s]
Loading 0:  84%|████████▍ | 305/363 [00:14<00:22,  2.57it/s]
Loading 0:  85%|████████▌ | 309/363 [00:14<00:16,  3.30it/s]
Loading 0:  86%|████████▌ | 313/363 [00:14<00:11,  4.27it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:06,  6.69it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:04,  9.15it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:02, 11.74it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 16.58it/s]
Loading 0:  94%|█████████▍| 343/363 [00:14<00:00, 20.11it/s]
Loading 0:  96%|█████████▌| 348/363 [00:15<00:00, 22.33it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 30.54it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 33.67it/s]
                                                            
Job chaiml-mistral-nemo-simp-2479-v2-mkmlizer completed after 95.02s with status: succeeded
Stopping job with name chaiml-mistral-nemo-simp-2479-v2-mkmlizer
Pipeline stage MKMLizer completed in 95.51s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-mistral-nemo-simp-2479-v2
Waiting for inference service chaiml-mistral-nemo-simp-2479-v2 to be ready
Inference service chaiml-mistral-nemo-simp-2479-v2 ready after 231.29957485198975s
Pipeline stage MKMLDeployer completed in 231.82s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.789090871810913s
Received healthy response to inference request in 1.1688861846923828s
Received healthy response to inference request in 1.7316296100616455s
Received healthy response to inference request in 1.4288763999938965s
Received healthy response to inference request in 0.9692192077636719s
5 requests
0 failed requests
5th percentile: 1.009152603149414
10th percentile: 1.0490859985351562
20th percentile: 1.1289527893066407
30th percentile: 1.2208842277526855
40th percentile: 1.324880313873291
50th percentile: 1.4288763999938965
60th percentile: 1.549977684020996
70th percentile: 1.6710789680480957
80th percentile: 1.743121862411499
90th percentile: 1.766106367111206
95th percentile: 1.7775986194610596
99th percentile: 1.7867924213409423
mean time: 1.4175404548645019
Pipeline stage StressChecker completed in 8.44s
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 2.23s
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 2.10s
Shutdown handler de-registered
chaiml-mistral-nemo-simp_2479_v2 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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-mistral-nemo-simp-2479-v2-profiler
Waiting for inference service chaiml-mistral-nemo-simp-2479-v2-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 3029.53s
Shutdown handler de-registered
chaiml-mistral-nemo-simp_2479_v2 status is now inactive due to auto deactivation removed underperforming models