chaiml-mistral-nemo-simp_2320

developer_uid: azuruce

submission_id: chaiml-mistral-nemo-simp_2320_v3

model_name: chaiml-mistral-nemo-simp_2320_v3

model_group: ChaiML/mistral_nemo_simp

status: inactive

timestamp: 2024-12-15T23:17:20+00:00

num_battles: 8759

num_wins: 4184

celo_rating: 1214.51

family_friendly_score: 0.5744

family_friendly_standard_error: 0.006992347817435857

submission_type: basic

model_repo: ChaiML/mistral_nemo_simpo_baseline_albert_20241213_v1-checkpoint-1560

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6352941253629111, 'latency_mean': 1.5740144371986389, 'latency_p50': 1.5803579092025757, 'latency_p90': 1.7261183261871338}, {'batch_size': 3, 'throughput': 1.2761325585409127, 'latency_mean': 2.341848864555359, 'latency_p50': 2.3399122953414917, 'latency_p90': 2.5763449192047116}, {'batch_size': 5, 'throughput': 1.622865503496541, 'latency_mean': 3.0736260068416597, 'latency_p50': 3.079257011413574, 'latency_p90': 3.426706576347351}, {'batch_size': 6, 'throughput': 1.7202507891365613, 'latency_mean': 3.461874396800995, 'latency_p50': 3.438549518585205, 'latency_p90': 3.9480762481689453}, {'batch_size': 8, 'throughput': 1.883980763516041, 'latency_mean': 4.221498547792435, 'latency_p50': 4.198598861694336, 'latency_p90': 4.774057698249817}, {'batch_size': 10, 'throughput': 1.988496905071295, 'latency_mean': 5.003613122701645, 'latency_p50': 5.054640769958496, 'latency_p90': 5.666482925415039}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-mistral-nemo-simp_2320_v3

is_internal_developer: True

language_model: ChaiML/mistral_nemo_simpo_baseline_albert_20241213_v1-checkpoint-1560

model_size: 13B

ranking_group: single

throughput_3p7s: 1.79

us_pacific_date: 2024-12-15

win_ratio: 0.47768010046808995

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-2320-v3-mkmlizer
Waiting for job on chaiml-mistral-nemo-simp-2320-v3-mkmlizer to finish
chaiml-mistral-nemo-simp-2320-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-nemo-simp-2320-v3-mkmlizer: ║     _____            __           __                                ║
chaiml-mistral-nemo-simp-2320-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-mistral-nemo-simp-2320-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-mistral-nemo-simp-2320-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-mistral-nemo-simp-2320-v3-mkmlizer: ║       /___/                                                         ║
chaiml-mistral-nemo-simp-2320-v3-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-simp-2320-v3-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-mistral-nemo-simp-2320-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-mistral-nemo-simp-2320-v3-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral-nemo-simp-2320-v3-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-simp-2320-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral-nemo-simp-2320-v3-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral-nemo-simp-2320-v3-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-simp-2320-v3-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral-nemo-simp-2320-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral-nemo-simp-2320-v3-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-mistral-nemo-simp-2320-v3-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-simp-2320-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral-nemo-simp-2320-v3-mkmlizer: Downloaded to shared memory in 32.137s
chaiml-mistral-nemo-simp-2320-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp4q3kq1_5, device:0
chaiml-mistral-nemo-simp-2320-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral-nemo-simp-2320-v3-mkmlizer: quantized model in 38.730s
chaiml-mistral-nemo-simp-2320-v3-mkmlizer: Processed model ChaiML/mistral_nemo_simpo_baseline_albert_20241213_v1-checkpoint-1560 in 70.867s
chaiml-mistral-nemo-simp-2320-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-nemo-simp-2320-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-nemo-simp-2320-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-nemo-simp-2320-v3
chaiml-mistral-nemo-simp-2320-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral-nemo-simp-2320-v3/special_tokens_map.json
chaiml-mistral-nemo-simp-2320-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-simp-2320-v3/config.json
chaiml-mistral-nemo-simp-2320-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-simp-2320-v3/tokenizer_config.json
chaiml-mistral-nemo-simp-2320-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral-nemo-simp-2320-v3/tokenizer.json
chaiml-mistral-nemo-simp-2320-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-nemo-simp-2320-v3/flywheel_model.0.safetensors
chaiml-mistral-nemo-simp-2320-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:13, 26.98it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:07, 45.39it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:07, 46.54it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:09, 36.20it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:07, 44.56it/s]
Loading 0:  10%|▉         | 35/363 [00:00<00:07, 42.41it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:08, 39.84it/s]
Loading 0:  12%|█▏        | 45/363 [00:01<00:08, 37.48it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:08, 36.68it/s]
Loading 0:  15%|█▍        | 53/363 [00:01<00:08, 37.28it/s]
Loading 0:  16%|█▌        | 58/363 [00:01<00:07, 40.26it/s]
Loading 0:  17%|█▋        | 63/363 [00:01<00:11, 25.88it/s]
Loading 0:  18%|█▊        | 67/363 [00:01<00:10, 26.94it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:10, 28.28it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:09, 28.95it/s]
Loading 0:  22%|██▏       | 80/363 [00:02<00:08, 32.14it/s]
Loading 0:  23%|██▎       | 84/363 [00:02<00:08, 31.88it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:07, 35.24it/s]
Loading 0:  26%|██▌       | 93/363 [00:02<00:07, 34.32it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:07, 34.68it/s]
Loading 0:  28%|██▊       | 102/363 [00:02<00:08, 31.96it/s]
Loading 0:  29%|██▉       | 106/363 [00:03<00:07, 32.77it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:06, 38.48it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:06, 36.53it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:07, 34.63it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:06, 38.31it/s]
Loading 0:  36%|███▌      | 129/363 [00:03<00:06, 35.11it/s]
Loading 0:  37%|███▋      | 134/363 [00:03<00:06, 36.73it/s]
Loading 0:  38%|███▊      | 138/363 [00:03<00:06, 35.01it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:09, 24.36it/s]
Loading 0:  40%|███▉      | 145/363 [00:04<00:09, 23.87it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:08, 24.46it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:06, 33.34it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:06, 32.50it/s]
Loading 0:  45%|████▌     | 165/363 [00:04<00:05, 36.04it/s]
Loading 0:  47%|████▋     | 169/363 [00:04<00:05, 34.66it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 37.05it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 35.41it/s]
Loading 0:  50%|█████     | 183/363 [00:05<00:04, 37.94it/s]
Loading 0:  52%|█████▏    | 187/363 [00:05<00:04, 36.16it/s]
Loading 0:  53%|█████▎    | 192/363 [00:05<00:04, 38.68it/s]
Loading 0:  54%|█████▍    | 196/363 [00:05<00:04, 36.44it/s]
Loading 0:  55%|█████▌    | 201/363 [00:05<00:04, 39.71it/s]
Loading 0:  57%|█████▋    | 206/363 [00:05<00:03, 39.46it/s]
Loading 0:  58%|█████▊    | 211/363 [00:06<00:03, 39.38it/s]
Loading 0:  60%|█████▉    | 216/363 [00:06<00:03, 41.65it/s]
Loading 0:  61%|██████    | 221/363 [00:06<00:03, 43.83it/s]
Loading 0:  62%|██████▏   | 226/363 [00:06<00:05, 26.17it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:04, 26.75it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 34.31it/s]
Loading 0:  67%|██████▋   | 242/363 [00:07<00:03, 35.04it/s]
Loading 0:  68%|██████▊   | 247/363 [00:07<00:03, 34.89it/s]
Loading 0:  69%|██████▉   | 251/363 [00:07<00:03, 33.15it/s]
Loading 0:  70%|███████   | 255/363 [00:07<00:03, 34.64it/s]
Loading 0:  71%|███████▏  | 259/363 [00:07<00:02, 35.58it/s]
Loading 0:  73%|███████▎  | 265/363 [00:07<00:02, 40.88it/s]
Loading 0:  75%|███████▍  | 271/363 [00:07<00:02, 40.35it/s]
Loading 0:  76%|███████▌  | 276/363 [00:07<00:02, 40.83it/s]
Loading 0:  78%|███████▊  | 283/363 [00:08<00:01, 46.66it/s]
Loading 0:  80%|███████▉  | 289/363 [00:08<00:01, 42.33it/s]
Loading 0:  81%|████████  | 294/363 [00:08<00:01, 38.30it/s]
Loading 0:  82%|████████▏ | 299/363 [00:08<00:01, 39.19it/s]
Loading 0:  84%|████████▎ | 304/363 [00:15<00:24,  2.39it/s]
Loading 0:  85%|████████▍ | 307/363 [00:15<00:19,  2.90it/s]
Loading 0:  86%|████████▌ | 312/363 [00:15<00:12,  4.09it/s]
Loading 0:  88%|████████▊ | 320/363 [00:15<00:06,  6.77it/s]
Loading 0:  90%|████████▉ | 326/363 [00:16<00:04,  9.13it/s]
Loading 0:  91%|█████████ | 331/363 [00:16<00:02, 11.44it/s]
Loading 0:  93%|█████████▎| 337/363 [00:16<00:01, 15.27it/s]
Loading 0:  94%|█████████▍| 342/363 [00:16<00:01, 18.15it/s]
Loading 0:  96%|█████████▌| 347/363 [00:16<00:00, 21.67it/s]
Loading 0:  97%|█████████▋| 352/363 [00:16<00:00, 25.33it/s]
Loading 0:  98%|█████████▊| 357/363 [00:16<00:00, 25.06it/s]
                                                            
Job chaiml-mistral-nemo-simp-2320-v3-mkmlizer completed after 105.91s with status: succeeded
Stopping job with name chaiml-mistral-nemo-simp-2320-v3-mkmlizer
Pipeline stage MKMLizer completed in 106.46s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-mistral-nemo-simp-2320-v3
Waiting for inference service chaiml-mistral-nemo-simp-2320-v3 to be ready
Failed to get response for submission chaiml-mistral-nemo-simp_3795_v1: ('http://chaiml-mistral-nemo-simp-3795-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:42306->127.0.0.1:8080: read: connection reset by peer\n')
Inference service chaiml-mistral-nemo-simp-2320-v3 ready after 220.99783515930176s
Pipeline stage MKMLDeployer completed in 221.60s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9527113437652588s
Received healthy response to inference request in 1.6612226963043213s
Received healthy response to inference request in 1.7384734153747559s
Received healthy response to inference request in 1.4731791019439697s
Received healthy response to inference request in 1.2684741020202637s
5 requests
0 failed requests
5th percentile: 1.3094151020050049
10th percentile: 1.350356101989746
20th percentile: 1.4322381019592285
30th percentile: 1.5107878208160401
40th percentile: 1.5860052585601807
50th percentile: 1.6612226963043213
60th percentile: 1.6921229839324952
70th percentile: 1.723023271560669
80th percentile: 1.7813210010528564
90th percentile: 1.8670161724090577
95th percentile: 1.9098637580871582
99th percentile: 1.9441418266296386
mean time: 1.618812131881714
Pipeline stage StressChecker completed in 9.57s
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 2.41s
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 2.80s
Shutdown handler de-registered
chaiml-mistral-nemo-simp_2320_v3 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 2464.61s
Shutdown handler de-registered
chaiml-mistral-nemo-simp_2320_v3 status is now inactive due to auto deactivation removed underperforming models