chaiml-mistral-nemo-dpo-_3876

developer_uid: azuruce

submission_id: chaiml-mistral-nemo-dpo-_3876_v1

model_name: chaiml-mistral-nemo-dpo-_3876_v1

model_group: ChaiML/mistral_nemo_dpo_

status: inactive

timestamp: 2024-12-12T08:50:01+00:00

num_battles: 10870

num_wins: 5280

celo_rating: 1252.56

family_friendly_score: 0.5760000000000001

family_friendly_standard_error: 0.0069889054937092975

submission_type: basic

model_repo: ChaiML/mistral_nemo_dpo_baseline_albert_241210_10k_v4

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6395962363328332, 'latency_mean': 1.5634204363822937, 'latency_p50': 1.5601569414138794, 'latency_p90': 1.7141318559646606}, {'batch_size': 4, 'throughput': 1.5033399344193445, 'latency_mean': 2.649785761833191, 'latency_p50': 2.626986861228943, 'latency_p90': 2.922572565078735}, {'batch_size': 5, 'throughput': 1.633172266611211, 'latency_mean': 3.0465719854831694, 'latency_p50': 3.044681191444397, 'latency_p90': 3.3706701040267943}, {'batch_size': 8, 'throughput': 1.9248036076814354, 'latency_mean': 4.1278459835052494, 'latency_p50': 4.1227699518203735, 'latency_p90': 4.65879259109497}, {'batch_size': 10, 'throughput': 2.0020498760205676, 'latency_mean': 4.963947772979736, 'latency_p50': 4.998229146003723, 'latency_p90': 5.618358755111695}, {'batch_size': 12, 'throughput': 2.0678547782515664, 'latency_mean': 5.756104007959366, 'latency_p50': 5.763934254646301, 'latency_p90': 6.468402051925659}, {'batch_size': 15, 'throughput': 2.115335188594286, 'latency_mean': 7.010277280807495, 'latency_p50': 7.000695466995239, 'latency_p90': 7.848245310783386}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-mistral-nemo-dpo-_3876_v1

is_internal_developer: True

language_model: ChaiML/mistral_nemo_dpo_baseline_albert_241210_10k_v4

model_size: 13B

ranking_group: single

throughput_3p7s: 1.84

us_pacific_date: 2024-12-12

win_ratio: 0.48574057037718493

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-3876-v1-mkmlizer
Waiting for job on chaiml-mistral-nemo-dpo-3876-v1-mkmlizer to finish
chaiml-mistral-nemo-dpo-3876-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-nemo-dpo-3876-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-mistral-nemo-dpo-3876-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-mistral-nemo-dpo-3876-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-mistral-nemo-dpo-3876-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-mistral-nemo-dpo-3876-v1-mkmlizer: ║       /___/                                                         ║
chaiml-mistral-nemo-dpo-3876-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-3876-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-mistral-nemo-dpo-3876-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-mistral-nemo-dpo-3876-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral-nemo-dpo-3876-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-3876-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral-nemo-dpo-3876-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral-nemo-dpo-3876-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-3876-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral-nemo-dpo-3876-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral-nemo-dpo-3876-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-mistral-nemo-dpo-3876-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-3876-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral-nemo-dpo-3876-v1-mkmlizer: Downloaded to shared memory in 48.124s
chaiml-mistral-nemo-dpo-3876-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpcva2sq9r, device:0
chaiml-mistral-nemo-dpo-3876-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral-nemo-dpo-3876-v1-mkmlizer: quantized model in 37.286s
chaiml-mistral-nemo-dpo-3876-v1-mkmlizer: Processed model ChaiML/mistral_nemo_dpo_baseline_albert_241210_10k_v4 in 85.410s
chaiml-mistral-nemo-dpo-3876-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-nemo-dpo-3876-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-nemo-dpo-3876-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-3876-v1
chaiml-mistral-nemo-dpo-3876-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-3876-v1/config.json
chaiml-mistral-nemo-dpo-3876-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-3876-v1/special_tokens_map.json
chaiml-mistral-nemo-dpo-3876-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-3876-v1/tokenizer_config.json
chaiml-mistral-nemo-dpo-3876-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-3876-v1/tokenizer.json
chaiml-mistral-nemo-dpo-3876-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-3876-v1/flywheel_model.0.safetensors
chaiml-mistral-nemo-dpo-3876-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 27.73it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 47.13it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 43.56it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 41.49it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 47.74it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 45.23it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 43.92it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 49.31it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 45.21it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 33.14it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 31.90it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 38.09it/s]
Loading 0:  21%|██        | 77/363 [00:01<00:07, 40.47it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:07, 36.48it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:06, 44.43it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:06, 43.70it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:06, 42.75it/s]
Loading 0:  29%|██▉       | 107/363 [00:02<00:05, 46.85it/s]
Loading 0:  31%|███       | 113/363 [00:02<00:05, 42.91it/s]
Loading 0:  33%|███▎      | 118/363 [00:02<00:05, 41.10it/s]
Loading 0:  34%|███▍      | 125/363 [00:02<00:05, 46.66it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 43.72it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 43.00it/s]
Loading 0:  39%|███▉      | 141/363 [00:03<00:05, 41.43it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:07, 28.87it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:07, 29.33it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:05, 35.93it/s]
Loading 0:  45%|████▍     | 162/363 [00:04<00:05, 38.15it/s]
Loading 0:  46%|████▌     | 167/363 [00:04<00:05, 32.68it/s]
Loading 0:  48%|████▊     | 174/363 [00:04<00:04, 39.06it/s]
Loading 0:  49%|████▉     | 179/363 [00:04<00:04, 38.92it/s]
Loading 0:  51%|█████     | 184/363 [00:04<00:04, 38.77it/s]
Loading 0:  52%|█████▏    | 189/363 [00:04<00:04, 40.11it/s]
Loading 0:  53%|█████▎    | 194/363 [00:04<00:04, 34.21it/s]
Loading 0:  55%|█████▌    | 201/363 [00:05<00:03, 40.62it/s]
Loading 0:  57%|█████▋    | 206/363 [00:05<00:03, 40.10it/s]
Loading 0:  58%|█████▊    | 211/363 [00:05<00:03, 41.01it/s]
Loading 0:  60%|█████▉    | 216/363 [00:05<00:03, 42.21it/s]
Loading 0:  61%|██████    | 221/363 [00:05<00:03, 43.26it/s]
Loading 0:  62%|██████▏   | 226/363 [00:05<00:05, 26.09it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:05, 26.39it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 33.67it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 35.08it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:03, 36.44it/s]
Loading 0:  69%|██████▉   | 252/363 [00:06<00:02, 38.81it/s]
Loading 0:  71%|███████   | 257/363 [00:06<00:03, 33.52it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 42.06it/s]
Loading 0:  74%|███████▍  | 270/363 [00:06<00:02, 43.71it/s]
Loading 0:  76%|███████▌  | 275/363 [00:07<00:02, 36.74it/s]
Loading 0:  78%|███████▊  | 282/363 [00:07<00:01, 44.11it/s]
Loading 0:  79%|███████▉  | 287/363 [00:07<00:01, 43.16it/s]
Loading 0:  80%|████████  | 292/363 [00:07<00:01, 43.79it/s]
Loading 0:  82%|████████▏ | 297/363 [00:07<00:01, 45.08it/s]
Loading 0:  83%|████████▎ | 303/363 [00:07<00:01, 43.13it/s]
Loading 0:  85%|████████▍ | 308/363 [00:14<00:22,  2.46it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:16,  3.17it/s]
Loading 0:  88%|████████▊ | 319/363 [00:14<00:08,  4.95it/s]
Loading 0:  89%|████████▉ | 324/363 [00:15<00:05,  6.57it/s]
Loading 0:  91%|█████████ | 329/363 [00:15<00:03,  8.68it/s]
Loading 0:  92%|█████████▏| 335/363 [00:15<00:02, 11.67it/s]
Loading 0:  94%|█████████▎| 340/363 [00:15<00:01, 14.44it/s]
Loading 0:  95%|█████████▌| 346/363 [00:15<00:00, 19.12it/s]
Loading 0:  97%|█████████▋| 351/363 [00:15<00:00, 22.63it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 26.50it/s]
Loading 0:  99%|█████████▉| 361/363 [00:15<00:00, 30.24it/s]
                                                            
Job chaiml-mistral-nemo-dpo-3876-v1-mkmlizer completed after 114.91s with status: succeeded
Stopping job with name chaiml-mistral-nemo-dpo-3876-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.43s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.20s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-mistral-nemo-dpo-3876-v1
Waiting for inference service chaiml-mistral-nemo-dpo-3876-v1 to be ready
Inference service chaiml-mistral-nemo-dpo-3876-v1 ready after 191.13138818740845s
Pipeline stage MKMLDeployer completed in 191.68s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8012118339538574s
Received healthy response to inference request in 1.5074472427368164s
Received healthy response to inference request in 1.1289122104644775s
Received healthy response to inference request in 1.325199842453003s
Received healthy response to inference request in 0.8547549247741699s
5 requests
0 failed requests
5th percentile: 0.9095863819122314
10th percentile: 0.964417839050293
20th percentile: 1.074080753326416
30th percentile: 1.1681697368621826
40th percentile: 1.2466847896575928
50th percentile: 1.325199842453003
60th percentile: 1.3980988025665284
70th percentile: 1.4709977626800537
80th percentile: 1.5662001609802247
90th percentile: 1.683705997467041
95th percentile: 1.742458915710449
99th percentile: 1.7894612503051757
mean time: 1.3235052108764649
Pipeline stage StressChecker completed in 7.92s
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 2.26s
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 2.05s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_3876_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 0.11s
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-3876-v1-profiler
Waiting for inference service chaiml-mistral-nemo-dpo-3876-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 2423.69s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_3876_v1 status is now inactive due to auto deactivation removed underperforming models