chaiml-mistral-nemo-dpo-_2482

developer_uid: azuruce

submission_id: chaiml-mistral-nemo-dpo-_2482_v1

model_name: chaiml-mistral-nemo-dpo-_2482_v1

model_group: ChaiML/mistral_nemo_dpo_

status: inactive

timestamp: 2024-12-17T21:53:47+00:00

num_battles: 16877

num_wins: 8208

celo_rating: 1253.5

family_friendly_score: 0.5760000000000001

family_friendly_standard_error: 0.0069889054937092975

submission_type: basic

model_repo: ChaiML/mistral_nemo_dpo_241217_albert_v1-checkpoint-1248

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6368612209791076, 'latency_mean': 1.5701115548610687, 'latency_p50': 1.5557219982147217, 'latency_p90': 1.748410415649414}, {'batch_size': 3, 'throughput': 1.2500660603385625, 'latency_mean': 2.3931603121757505, 'latency_p50': 2.3911975622177124, 'latency_p90': 2.6094795942306517}, {'batch_size': 5, 'throughput': 1.571482258509383, 'latency_mean': 3.1634663236141205, 'latency_p50': 3.1488293409347534, 'latency_p90': 3.6324293851852416}, {'batch_size': 6, 'throughput': 1.6862694855117022, 'latency_mean': 3.5416067707538605, 'latency_p50': 3.5544570684432983, 'latency_p90': 3.953032302856445}, {'batch_size': 8, 'throughput': 1.8474775555344471, 'latency_mean': 4.303671898841858, 'latency_p50': 4.303832411766052, 'latency_p90': 4.935225653648376}, {'batch_size': 10, 'throughput': 1.9050386575705045, 'latency_mean': 5.1923137176036835, 'latency_p50': 5.201094150543213, 'latency_p90': 5.924762010574341}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-mistral-nemo-dpo-_2482_v1

is_internal_developer: True

language_model: ChaiML/mistral_nemo_dpo_241217_albert_v1-checkpoint-1248

model_size: 13B

ranking_group: single

throughput_3p7s: 1.73

us_pacific_date: 2024-12-17

win_ratio: 0.4863423594240683

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-2482-v1-mkmlizer
Waiting for job on chaiml-mistral-nemo-dpo-2482-v1-mkmlizer to finish
chaiml-mistral-nemo-dpo-2482-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-nemo-dpo-2482-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-mistral-nemo-dpo-2482-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-mistral-nemo-dpo-2482-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-mistral-nemo-dpo-2482-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-mistral-nemo-dpo-2482-v1-mkmlizer: ║       /___/                                                         ║
chaiml-mistral-nemo-dpo-2482-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-2482-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-mistral-nemo-dpo-2482-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-mistral-nemo-dpo-2482-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral-nemo-dpo-2482-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-2482-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral-nemo-dpo-2482-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral-nemo-dpo-2482-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-2482-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral-nemo-dpo-2482-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral-nemo-dpo-2482-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-mistral-nemo-dpo-2482-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-2482-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral-nemo-dpo-2482-v1-mkmlizer: Downloaded to shared memory in 49.099s
chaiml-mistral-nemo-dpo-2482-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpxjyi_kca, device:0
chaiml-mistral-nemo-dpo-2482-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral-nemo-dpo-2482-v1-mkmlizer: quantized model in 36.577s
chaiml-mistral-nemo-dpo-2482-v1-mkmlizer: Processed model ChaiML/mistral_nemo_dpo_241217_albert_v1-checkpoint-1248 in 85.676s
chaiml-mistral-nemo-dpo-2482-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-nemo-dpo-2482-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-nemo-dpo-2482-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-2482-v1
chaiml-mistral-nemo-dpo-2482-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-2482-v1/tokenizer.json
chaiml-mistral-nemo-dpo-2482-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-2482-v1/flywheel_model.0.safetensors
chaiml-mistral-nemo-dpo-2482-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:13, 26.73it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 46.86it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 44.52it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 42.55it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 49.24it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 46.19it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 44.47it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 49.44it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 47.03it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 35.13it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:08, 35.66it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 40.53it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:06, 42.26it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:06, 42.07it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:05, 47.35it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:06, 44.18it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:06, 40.83it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:06, 41.46it/s]
Loading 0:  31%|███       | 112/363 [00:02<00:05, 43.92it/s]
Loading 0:  32%|███▏      | 117/363 [00:02<00:06, 39.32it/s]
Loading 0:  34%|███▎      | 122/363 [00:02<00:06, 40.15it/s]
Loading 0:  35%|███▍      | 127/363 [00:03<00:06, 35.25it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 43.72it/s]
Loading 0:  39%|███▉      | 141/363 [00:03<00:05, 42.23it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:07, 29.73it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:07, 29.07it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 34.74it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 36.51it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 39.32it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:04, 41.51it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 36.95it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 44.55it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:03, 44.07it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 45.47it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:03, 43.30it/s]
Loading 0:  56%|█████▌    | 204/363 [00:05<00:03, 42.06it/s]
Loading 0:  58%|█████▊    | 211/363 [00:05<00:03, 47.24it/s]
Loading 0:  60%|█████▉    | 217/363 [00:05<00:03, 44.41it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:04, 33.60it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:04, 33.29it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:04, 32.45it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:03, 38.77it/s]
Loading 0:  67%|██████▋   | 243/363 [00:06<00:02, 40.55it/s]
Loading 0:  68%|██████▊   | 248/363 [00:06<00:03, 36.75it/s]
Loading 0:  70%|███████   | 255/363 [00:06<00:02, 42.30it/s]
Loading 0:  72%|███████▏  | 260/363 [00:06<00:02, 40.54it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 41.66it/s]
Loading 0:  74%|███████▍  | 270/363 [00:06<00:02, 43.58it/s]
Loading 0:  76%|███████▌  | 275/363 [00:06<00:02, 37.38it/s]
Loading 0:  78%|███████▊  | 283/363 [00:06<00:01, 45.74it/s]
Loading 0:  80%|███████▉  | 289/363 [00:07<00:01, 44.40it/s]
Loading 0:  81%|████████  | 294/363 [00:07<00:01, 43.91it/s]
Loading 0:  83%|████████▎ | 301/363 [00:07<00:01, 50.01it/s]
Loading 0:  85%|████████▍ | 307/363 [00:14<00:20,  2.78it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:13,  3.67it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:07,  5.67it/s]
Loading 0:  90%|████████▉ | 325/363 [00:14<00:05,  7.27it/s]
Loading 0:  91%|█████████ | 330/363 [00:14<00:03,  8.96it/s]
Loading 0:  93%|█████████▎| 338/363 [00:15<00:01, 13.27it/s]
Loading 0:  94%|█████████▍| 343/363 [00:15<00:01, 16.25it/s]
Loading 0:  96%|█████████▌| 348/363 [00:15<00:00, 18.18it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 25.22it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 28.42it/s]
                                                            
Job chaiml-mistral-nemo-dpo-2482-v1-mkmlizer completed after 116.01s with status: succeeded
Stopping job with name chaiml-mistral-nemo-dpo-2482-v1-mkmlizer
Pipeline stage MKMLizer completed in 116.51s
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-2482-v1
Waiting for inference service chaiml-mistral-nemo-dpo-2482-v1 to be ready
Inference service chaiml-mistral-nemo-dpo-2482-v1 ready after 231.3545527458191s
Pipeline stage MKMLDeployer completed in 231.89s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.070591449737549s
Received healthy response to inference request in 1.4886445999145508s
Received healthy response to inference request in 1.5311968326568604s
Received healthy response to inference request in 1.1545519828796387s
Received healthy response to inference request in 1.3525500297546387s
5 requests
0 failed requests
5th percentile: 1.1941515922546386
10th percentile: 1.2337512016296386
20th percentile: 1.3129504203796387
30th percentile: 1.3797689437866212
40th percentile: 1.434206771850586
50th percentile: 1.4886445999145508
60th percentile: 1.5056654930114746
70th percentile: 1.5226863861083983
80th percentile: 1.639075756072998
90th percentile: 1.8548336029052734
95th percentile: 1.9627125263214111
99th percentile: 2.049015665054321
mean time: 1.5195069789886475
Pipeline stage StressChecker completed in 8.75s
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 2.13s
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 1.98s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_2482_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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-mistral-nemo-dpo-2482-v1-profiler
Waiting for inference service chaiml-mistral-nemo-dpo-2482-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 3047.49s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_2482_v1 status is now inactive due to auto deactivation removed underperforming models