chaiml-mistral-nemo-simp_5737

developer_uid: azuruce

submission_id: chaiml-mistral-nemo-simp_5737_v1

model_name: chaiml-mistral-nemo-simp_5737_v1

model_group: ChaiML/mistral_nemo_simp

status: inactive

timestamp: 2024-12-16T20:41:44+00:00

num_battles: 12893

num_wins: 5545

celo_rating: 1214.74

family_friendly_score: 0.5760000000000001

family_friendly_standard_error: 0.0069889054937092975

submission_type: basic

model_repo: ChaiML/mistral_nemo_simpo_baseline_albert_20241213_v1-checkpoint-1560-run_fix2

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6328916588307235, 'latency_mean': 1.5799898409843445, 'latency_p50': 1.5898576974868774, 'latency_p90': 1.7308804988861084}, {'batch_size': 3, 'throughput': 1.2644819798541318, 'latency_mean': 2.3606177628040315, 'latency_p50': 2.359518885612488, 'latency_p90': 2.6029802560806274}, {'batch_size': 5, 'throughput': 1.5998289642080825, 'latency_mean': 3.110022360086441, 'latency_p50': 3.153876543045044, 'latency_p90': 3.5076070070266723}, {'batch_size': 6, 'throughput': 1.7029874349343743, 'latency_mean': 3.5056489872932435, 'latency_p50': 3.5195127725601196, 'latency_p90': 3.945498514175415}, {'batch_size': 8, 'throughput': 1.8591713631979039, 'latency_mean': 4.275934890508652, 'latency_p50': 4.298177361488342, 'latency_p90': 4.843133020401001}, {'batch_size': 10, 'throughput': 1.9399814582389117, 'latency_mean': 5.119199951887131, 'latency_p50': 5.1183165311813354, 'latency_p90': 5.762672281265258}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-mistral-nemo-simp_5737_v1

is_internal_developer: True

language_model: ChaiML/mistral_nemo_simpo_baseline_albert_20241213_v1-checkpoint-1560-run_fix2

model_size: 13B

ranking_group: single

throughput_3p7s: 1.76

us_pacific_date: 2024-12-16

win_ratio: 0.4300783370821376

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-5737-v1-mkmlizer
Waiting for job on chaiml-mistral-nemo-simp-5737-v1-mkmlizer to finish
chaiml-mistral-nemo-simp-5737-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-nemo-simp-5737-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-mistral-nemo-simp-5737-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-mistral-nemo-simp-5737-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-mistral-nemo-simp-5737-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-mistral-nemo-simp-5737-v1-mkmlizer: ║       /___/                                                         ║
chaiml-mistral-nemo-simp-5737-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-simp-5737-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-mistral-nemo-simp-5737-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-mistral-nemo-simp-5737-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral-nemo-simp-5737-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-simp-5737-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral-nemo-simp-5737-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral-nemo-simp-5737-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-simp-5737-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral-nemo-simp-5737-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral-nemo-simp-5737-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-mistral-nemo-simp-5737-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-simp-5737-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral-nemo-simp-5737-v1-mkmlizer: Downloaded to shared memory in 48.436s
chaiml-mistral-nemo-simp-5737-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp9j073nsf, device:0
chaiml-mistral-nemo-simp-5737-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral-nemo-simp-5737-v1-mkmlizer: quantized model in 36.102s
chaiml-mistral-nemo-simp-5737-v1-mkmlizer: Processed model ChaiML/mistral_nemo_simpo_baseline_albert_20241213_v1-checkpoint-1560-run_fix2 in 84.538s
chaiml-mistral-nemo-simp-5737-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-nemo-simp-5737-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-nemo-simp-5737-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-nemo-simp-5737-v1
chaiml-mistral-nemo-simp-5737-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-simp-5737-v1/config.json
chaiml-mistral-nemo-simp-5737-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral-nemo-simp-5737-v1/special_tokens_map.json
chaiml-mistral-nemo-simp-5737-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-simp-5737-v1/tokenizer_config.json
chaiml-mistral-nemo-simp-5737-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-nemo-simp-5737-v1/flywheel_model.0.safetensors
chaiml-mistral-nemo-simp-5737-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 28.99it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 47.92it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 43.21it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 41.64it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:07, 47.10it/s]
Loading 0:  10%|▉         | 36/363 [00:00<00:06, 47.62it/s]
Loading 0:  11%|█▏        | 41/363 [00:00<00:08, 39.25it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 47.93it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 44.02it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:06, 44.93it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:10, 29.79it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:08, 35.16it/s]
Loading 0:  21%|██        | 76/363 [00:01<00:07, 37.02it/s]
Loading 0:  22%|██▏       | 81/363 [00:02<00:07, 38.93it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:06, 40.71it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:08, 33.50it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:06, 40.84it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:06, 41.62it/s]
Loading 0:  30%|███       | 109/363 [00:02<00:05, 45.92it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:06, 40.04it/s]
Loading 0:  33%|███▎      | 119/363 [00:02<00:06, 38.75it/s]
Loading 0:  35%|███▍      | 126/363 [00:03<00:05, 44.54it/s]
Loading 0:  36%|███▋      | 132/363 [00:03<00:05, 42.57it/s]
Loading 0:  38%|███▊      | 137/363 [00:03<00:05, 41.80it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 33.00it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 33.94it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 32.93it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:05, 39.97it/s]
Loading 0:  45%|████▍     | 163/363 [00:04<00:05, 39.72it/s]
Loading 0:  46%|████▋     | 168/363 [00:04<00:04, 40.78it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:04, 46.03it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:04, 44.12it/s]
Loading 0:  51%|█████     | 186/363 [00:04<00:04, 43.36it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 48.23it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:03, 44.51it/s]
Loading 0:  56%|█████▌    | 204/363 [00:05<00:03, 42.81it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 45.24it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 45.14it/s]
Loading 0:  61%|██████    | 221/363 [00:05<00:02, 48.44it/s]
Loading 0:  62%|██████▏   | 226/363 [00:05<00:04, 31.38it/s]
Loading 0:  63%|██████▎   | 230/363 [00:05<00:04, 30.27it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:03, 39.20it/s]
Loading 0:  67%|██████▋   | 244/363 [00:06<00:03, 39.45it/s]
Loading 0:  69%|██████▊   | 249/363 [00:06<00:02, 39.56it/s]
Loading 0:  70%|███████   | 255/363 [00:06<00:02, 43.49it/s]
Loading 0:  72%|███████▏  | 260/363 [00:06<00:02, 44.00it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 44.97it/s]
Loading 0:  75%|███████▍  | 271/363 [00:06<00:02, 43.05it/s]
Loading 0:  76%|███████▌  | 276/363 [00:06<00:02, 41.88it/s]
Loading 0:  78%|███████▊  | 282/363 [00:06<00:01, 46.23it/s]
Loading 0:  79%|███████▉  | 287/363 [00:06<00:01, 45.78it/s]
Loading 0:  80%|████████  | 292/363 [00:07<00:01, 45.53it/s]
Loading 0:  82%|████████▏ | 297/363 [00:07<00:01, 46.48it/s]
Loading 0:  83%|████████▎ | 302/363 [00:07<00:01, 47.20it/s]
Loading 0:  85%|████████▍ | 307/363 [00:14<00:23,  2.38it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:15,  3.30it/s]
Loading 0:  88%|████████▊ | 319/363 [00:14<00:08,  5.09it/s]
Loading 0:  89%|████████▉ | 324/363 [00:14<00:05,  6.71it/s]
Loading 0:  91%|█████████ | 329/363 [00:14<00:03,  8.85it/s]
Loading 0:  92%|█████████▏| 335/363 [00:14<00:02, 11.81it/s]
Loading 0:  94%|█████████▎| 340/363 [00:14<00:01, 14.73it/s]
Loading 0:  95%|█████████▌| 346/363 [00:15<00:00, 19.48it/s]
Loading 0:  97%|█████████▋| 351/363 [00:15<00:00, 22.58it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 26.20it/s]
Loading 0:  99%|█████████▉| 361/363 [00:15<00:00, 29.82it/s]
                                                            
Job chaiml-mistral-nemo-simp-5737-v1-mkmlizer completed after 104.93s with status: succeeded
Stopping job with name chaiml-mistral-nemo-simp-5737-v1-mkmlizer
Pipeline stage MKMLizer completed in 105.55s
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-5737-v1
Waiting for inference service chaiml-mistral-nemo-simp-5737-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service chaiml-mistral-nemo-simp-5737-v1 ready after 220.77349948883057s
Pipeline stage MKMLDeployer completed in 221.36s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9681615829467773s
Received healthy response to inference request in 1.4173681735992432s
Received healthy response to inference request in 1.4323694705963135s
Received healthy response to inference request in 1.4926741123199463s
Received healthy response to inference request in 1.395348072052002s
5 requests
0 failed requests
5th percentile: 1.3997520923614502
10th percentile: 1.4041561126708983
20th percentile: 1.412964153289795
30th percentile: 1.4203684329986572
40th percentile: 1.4263689517974854
50th percentile: 1.4323694705963135
60th percentile: 1.4564913272857667
70th percentile: 1.4806131839752197
80th percentile: 1.5877716064453127
90th percentile: 1.777966594696045
95th percentile: 1.873064088821411
99th percentile: 1.949142084121704
mean time: 1.5411842823028565
Pipeline stage StressChecker completed in 9.01s
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 2.17s
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 2.03s
Shutdown handler de-registered
chaiml-mistral-nemo-simp_5737_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 2886.33s
Shutdown handler de-registered
chaiml-mistral-nemo-simp_5737_v1 status is now inactive due to auto deactivation removed underperforming models