chaiml-mistral-nemo-dpo-_8081

developer_uid: azuruce

submission_id: chaiml-mistral-nemo-dpo-_8081_v1

model_name: chaiml-mistral-nemo-dpo-_8081_v1

model_group: ChaiML/mistral_nemo_dpo_

status: torndown

timestamp: 2024-12-10T09:22:25+00:00

num_battles: 11067

num_wins: 3181

celo_rating: 1102.06

family_friendly_score: 0.5876

family_friendly_standard_error: 0.006961698643291018

submission_type: basic

model_repo: ChaiML/mistral_nemo_dpo_baseline_albert_241210_v1

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6353072733940313, 'latency_mean': 1.5739848017692566, 'latency_p50': 1.57869291305542, 'latency_p90': 1.726340889930725}, {'batch_size': 3, 'throughput': 1.2590863463935358, 'latency_mean': 2.374870434999466, 'latency_p50': 2.3662058115005493, 'latency_p90': 2.6195404529571533}, {'batch_size': 5, 'throughput': 1.5695701961225916, 'latency_mean': 3.165428249835968, 'latency_p50': 3.1519025564193726, 'latency_p90': 3.5286636352539062}, {'batch_size': 6, 'throughput': 1.6764798380898462, 'latency_mean': 3.550010454654694, 'latency_p50': 3.5677316188812256, 'latency_p90': 4.028507995605469}, {'batch_size': 8, 'throughput': 1.8330490033452904, 'latency_mean': 4.331428269147873, 'latency_p50': 4.360566854476929, 'latency_p90': 4.841790676116943}, {'batch_size': 10, 'throughput': 1.9173963158862413, 'latency_mean': 5.172157504558563, 'latency_p50': 5.167119026184082, 'latency_p90': 5.813089656829834}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-mistral-nemo-dpo-_8081_v1

is_internal_developer: True

language_model: ChaiML/mistral_nemo_dpo_baseline_albert_241210_v1

model_size: 13B

ranking_group: single

throughput_3p7s: 1.73

us_pacific_date: 2024-12-10

win_ratio: 0.28743110147284723

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-dpo-8081-v1-mkmlizer
Waiting for job on chaiml-mistral-nemo-dpo-8081-v1-mkmlizer to finish
chaiml-mistral-nemo-dpo-8081-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-nemo-dpo-8081-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-mistral-nemo-dpo-8081-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-mistral-nemo-dpo-8081-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-mistral-nemo-dpo-8081-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-mistral-nemo-dpo-8081-v1-mkmlizer: ║       /___/                                                         ║
chaiml-mistral-nemo-dpo-8081-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-8081-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-mistral-nemo-dpo-8081-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-mistral-nemo-dpo-8081-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral-nemo-dpo-8081-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-8081-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral-nemo-dpo-8081-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral-nemo-dpo-8081-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-8081-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral-nemo-dpo-8081-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral-nemo-dpo-8081-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-mistral-nemo-dpo-8081-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-8081-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral-nemo-dpo-8081-v1-mkmlizer: Downloaded to shared memory in 46.987s
chaiml-mistral-nemo-dpo-8081-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpmwcnhsjk, device:0
chaiml-mistral-nemo-dpo-8081-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral-nemo-dpo-8081-v1-mkmlizer: quantized model in 36.772s
chaiml-mistral-nemo-dpo-8081-v1-mkmlizer: Processed model ChaiML/mistral_nemo_dpo_baseline_albert_241210_v1 in 83.759s
chaiml-mistral-nemo-dpo-8081-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-nemo-dpo-8081-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-nemo-dpo-8081-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-8081-v1
chaiml-mistral-nemo-dpo-8081-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-8081-v1/config.json
chaiml-mistral-nemo-dpo-8081-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-8081-v1/special_tokens_map.json
chaiml-mistral-nemo-dpo-8081-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-8081-v1/tokenizer_config.json
chaiml-mistral-nemo-dpo-8081-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-8081-v1/tokenizer.json
chaiml-mistral-nemo-dpo-8081-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:13, 26.25it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 47.04it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 44.20it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 41.90it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 48.31it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 46.34it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 44.75it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 49.53it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 46.58it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 35.17it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 33.93it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 40.53it/s]
Loading 0:  21%|██        | 77/363 [00:01<00:06, 42.59it/s]
Loading 0:  23%|██▎       | 82/363 [00:01<00:07, 38.03it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:06, 45.24it/s]
Loading 0:  26%|██▌       | 94/363 [00:02<00:06, 43.73it/s]
Loading 0:  27%|██▋       | 99/363 [00:02<00:05, 44.79it/s]
Loading 0:  29%|██▉       | 105/363 [00:02<00:05, 43.48it/s]
Loading 0:  31%|███       | 112/363 [00:02<00:05, 48.30it/s]
Loading 0:  32%|███▏      | 117/363 [00:02<00:05, 44.75it/s]
Loading 0:  34%|███▍      | 123/363 [00:02<00:05, 43.90it/s]
Loading 0:  35%|███▌      | 128/363 [00:02<00:05, 42.93it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:04, 47.63it/s]
Loading 0:  39%|███▉      | 141/363 [00:03<00:04, 45.37it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 31.31it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 31.52it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:05, 38.35it/s]
Loading 0:  45%|████▍     | 163/363 [00:03<00:05, 39.47it/s]
Loading 0:  46%|████▋     | 168/363 [00:04<00:04, 40.26it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:04, 46.18it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:04, 44.01it/s]
Loading 0:  51%|█████     | 186/363 [00:04<00:04, 41.94it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 46.26it/s]
Loading 0:  55%|█████▍    | 198/363 [00:04<00:03, 47.02it/s]
Loading 0:  56%|█████▌    | 203/363 [00:04<00:04, 38.46it/s]
Loading 0:  58%|█████▊    | 210/363 [00:04<00:03, 45.68it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 45.65it/s]
Loading 0:  61%|██████    | 222/363 [00:05<00:03, 45.99it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:04, 32.24it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:04, 31.40it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:03, 38.03it/s]
Loading 0:  67%|██████▋   | 243/363 [00:05<00:03, 39.51it/s]
Loading 0:  68%|██████▊   | 248/363 [00:06<00:03, 33.15it/s]
Loading 0:  71%|███████   | 256/363 [00:06<00:02, 41.32it/s]
Loading 0:  72%|███████▏  | 262/363 [00:06<00:02, 41.02it/s]
Loading 0:  74%|███████▎  | 267/363 [00:06<00:02, 40.16it/s]
Loading 0:  75%|███████▌  | 273/363 [00:06<00:02, 42.85it/s]
Loading 0:  77%|███████▋  | 278/363 [00:06<00:02, 41.98it/s]
Loading 0:  78%|███████▊  | 283/363 [00:06<00:01, 43.21it/s]
Loading 0:  79%|███████▉  | 288/363 [00:06<00:01, 44.44it/s]
Loading 0:  81%|████████  | 293/363 [00:07<00:01, 36.66it/s]
Loading 0:  82%|████████▏ | 299/363 [00:07<00:01, 40.05it/s]
Loading 0:  84%|████████▎ | 304/363 [00:14<00:24,  2.40it/s]
Loading 0:  85%|████████▍ | 307/363 [00:14<00:19,  2.92it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:12,  4.15it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:06,  6.87it/s]
Loading 0:  90%|████████▉ | 325/363 [00:14<00:04,  8.99it/s]
Loading 0:  91%|█████████ | 330/363 [00:14<00:02, 11.00it/s]
Loading 0:  93%|█████████▎| 338/363 [00:15<00:01, 16.50it/s]
Loading 0:  95%|█████████▍| 344/363 [00:15<00:00, 20.10it/s]
Loading 0:  96%|█████████▌| 349/363 [00:15<00:00, 23.37it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 29.69it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 32.53it/s]
                                                            
Job chaiml-mistral-nemo-dpo-8081-v1-mkmlizer completed after 115.05s with status: succeeded
Stopping job with name chaiml-mistral-nemo-dpo-8081-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.60s
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-dpo-8081-v1
Waiting for inference service chaiml-mistral-nemo-dpo-8081-v1 to be ready
Inference service chaiml-mistral-nemo-dpo-8081-v1 ready after 170.58656191825867s
Pipeline stage MKMLDeployer completed in 171.15s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1673831939697266s
Received healthy response to inference request in 1.3678405284881592s
Received healthy response to inference request in 0.9774518013000488s
Received healthy response to inference request in 1.0727126598358154s
Received healthy response to inference request in 0.7891843318939209s
5 requests
0 failed requests
5th percentile: 0.8268378257751465
10th percentile: 0.864491319656372
20th percentile: 0.9397983074188232
30th percentile: 0.9965039730072022
40th percentile: 1.0346083164215087
50th percentile: 1.0727126598358154
60th percentile: 1.190763807296753
70th percentile: 1.3088149547576904
80th percentile: 1.5277490615844729
90th percentile: 1.8475661277770996
95th percentile: 2.007474660873413
99th percentile: 2.135401487350464
mean time: 1.2749145030975342
Pipeline stage StressChecker completed in 7.82s
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 2.18s
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 1.95s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_8081_v1 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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-mistral-nemo-dpo-8081-v1-profiler
Waiting for inference service chaiml-mistral-nemo-dpo-8081-v1-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 2312.60s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_8081_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistral-nemo-dpo-_8081_v1 status is now torndown due to DeploymentManager action
chaiml-mistral-nemo-dpo-_8081_v1 status is now torndown due to DeploymentManager action
chaiml-mistral-nemo-dpo-_8081_v1 status is now torndown due to DeploymentManager action