chaiml-mistral-nemo-dpo-_1800

developer_uid: azuruce

submission_id: chaiml-mistral-nemo-dpo-_1800_v1

model_name: chaiml-mistral-nemo-dpo-_1800_v1

model_group: ChaiML/mistral_nemo_dpo_

status: inactive

timestamp: 2024-12-18T04:18:57+00:00

num_battles: 12902

num_wins: 6255

celo_rating: 1251.29

family_friendly_score: 0.5738

family_friendly_standard_error: 0.006993619377689924

submission_type: basic

model_repo: ChaiML/mistral_nemo_dpo_241217_albert_v1-checkpoint-1872

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6318184652113757, 'latency_mean': 1.582669676542282, 'latency_p50': 1.580273151397705, 'latency_p90': 1.7565528869628906}, {'batch_size': 3, 'throughput': 1.2590198413659326, 'latency_mean': 2.375418323278427, 'latency_p50': 2.369052767753601, 'latency_p90': 2.599934220314026}, {'batch_size': 5, 'throughput': 1.5887916802866449, 'latency_mean': 3.133352222442627, 'latency_p50': 3.1481462717056274, 'latency_p90': 3.5214515447616574}, {'batch_size': 6, 'throughput': 1.7043967453111681, 'latency_mean': 3.5089853584766386, 'latency_p50': 3.4843186140060425, 'latency_p90': 3.950400710105896}, {'batch_size': 8, 'throughput': 1.8491599929919535, 'latency_mean': 4.303874136209488, 'latency_p50': 4.272222518920898, 'latency_p90': 4.864140009880066}, {'batch_size': 10, 'throughput': 1.937998043461548, 'latency_mean': 5.1236960983276365, 'latency_p50': 5.144800782203674, 'latency_p90': 5.737146162986756}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-mistral-nemo-dpo-_1800_v1

is_internal_developer: True

language_model: ChaiML/mistral_nemo_dpo_241217_albert_v1-checkpoint-1872

model_size: 13B

ranking_group: single

throughput_3p7s: 1.75

us_pacific_date: 2024-12-17

win_ratio: 0.48480855681289725

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-1800-v1-mkmlizer
Waiting for job on chaiml-mistral-nemo-dpo-1800-v1-mkmlizer to finish
chaiml-mistral-nemo-dpo-1800-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-nemo-dpo-1800-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-mistral-nemo-dpo-1800-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-mistral-nemo-dpo-1800-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-mistral-nemo-dpo-1800-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-mistral-nemo-dpo-1800-v1-mkmlizer: ║       /___/                                                         ║
chaiml-mistral-nemo-dpo-1800-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-1800-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-mistral-nemo-dpo-1800-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-mistral-nemo-dpo-1800-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral-nemo-dpo-1800-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-1800-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral-nemo-dpo-1800-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral-nemo-dpo-1800-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-1800-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral-nemo-dpo-1800-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral-nemo-dpo-1800-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-mistral-nemo-dpo-1800-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-1800-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral-nemo-dpo-1800-v1-mkmlizer: Downloaded to shared memory in 48.846s
chaiml-mistral-nemo-dpo-1800-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpb4mcsbht, device:0
chaiml-mistral-nemo-dpo-1800-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral-nemo-dpo-1800-v1-mkmlizer: quantized model in 36.449s
chaiml-mistral-nemo-dpo-1800-v1-mkmlizer: Processed model ChaiML/mistral_nemo_dpo_241217_albert_v1-checkpoint-1872 in 85.295s
chaiml-mistral-nemo-dpo-1800-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-nemo-dpo-1800-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-nemo-dpo-1800-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-1800-v1
chaiml-mistral-nemo-dpo-1800-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-1800-v1/config.json
chaiml-mistral-nemo-dpo-1800-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-1800-v1/special_tokens_map.json
chaiml-mistral-nemo-dpo-1800-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-1800-v1/tokenizer_config.json
chaiml-mistral-nemo-dpo-1800-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-1800-v1/tokenizer.json
chaiml-mistral-nemo-dpo-1800-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-1800-v1/flywheel_model.0.safetensors
chaiml-mistral-nemo-dpo-1800-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:13, 26.94it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:07, 44.97it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:07, 46.62it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:09, 35.81it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:07, 44.16it/s]
Loading 0:  10%|▉         | 35/363 [00:00<00:07, 43.28it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:07, 43.34it/s]
Loading 0:  12%|█▏        | 45/363 [00:01<00:07, 44.17it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:08, 36.15it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:07, 41.64it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 30.80it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 30.23it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:08, 35.82it/s]
Loading 0:  21%|██        | 76/363 [00:01<00:07, 37.59it/s]
Loading 0:  22%|██▏       | 81/363 [00:02<00:07, 39.96it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:06, 42.10it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:07, 36.05it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:06, 43.52it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:06, 43.14it/s]
Loading 0:  30%|███       | 110/363 [00:02<00:05, 43.47it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:05, 44.24it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:05, 41.56it/s]
Loading 0:  35%|███▍      | 126/363 [00:03<00:05, 44.83it/s]
Loading 0:  36%|███▌      | 131/363 [00:03<00:05, 46.02it/s]
Loading 0:  37%|███▋      | 136/363 [00:03<00:06, 37.74it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 31.82it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 31.72it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:07, 29.88it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:05, 35.40it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:05, 35.48it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:04, 40.42it/s]
Loading 0:  47%|████▋     | 172/363 [00:04<00:04, 40.39it/s]
Loading 0:  49%|████▉     | 177/363 [00:04<00:04, 41.13it/s]
Loading 0:  51%|█████     | 184/363 [00:04<00:03, 46.74it/s]
Loading 0:  52%|█████▏    | 190/363 [00:04<00:03, 45.30it/s]
Loading 0:  54%|█████▎    | 195/363 [00:04<00:03, 43.95it/s]
Loading 0:  56%|█████▌    | 202/363 [00:05<00:03, 48.67it/s]
Loading 0:  57%|█████▋    | 208/363 [00:05<00:03, 45.80it/s]
Loading 0:  59%|█████▊    | 213/363 [00:05<00:03, 44.91it/s]
Loading 0:  60%|██████    | 219/363 [00:05<00:02, 48.58it/s]
Loading 0:  62%|██████▏   | 224/363 [00:05<00:04, 34.11it/s]
Loading 0:  63%|██████▎   | 229/363 [00:05<00:03, 34.55it/s]
Loading 0:  65%|██████▍   | 235/363 [00:05<00:03, 36.81it/s]
Loading 0:  66%|██████▌   | 240/363 [00:06<00:03, 38.47it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:02, 44.51it/s]
Loading 0:  70%|██████▉   | 253/363 [00:06<00:02, 43.73it/s]
Loading 0:  71%|███████   | 258/363 [00:06<00:02, 42.13it/s]
Loading 0:  73%|███████▎  | 264/363 [00:06<00:02, 44.90it/s]
Loading 0:  74%|███████▍  | 269/363 [00:06<00:02, 43.57it/s]
Loading 0:  75%|███████▌  | 274/363 [00:06<00:02, 43.94it/s]
Loading 0:  77%|███████▋  | 280/363 [00:06<00:01, 43.46it/s]
Loading 0:  79%|███████▊  | 285/363 [00:07<00:01, 43.70it/s]
Loading 0:  80%|████████  | 292/363 [00:07<00:01, 48.83it/s]
Loading 0:  82%|████████▏ | 298/363 [00:07<00:01, 46.31it/s]
Loading 0:  84%|████████▎ | 304/363 [00:14<00:21,  2.74it/s]
Loading 0:  85%|████████▍ | 308/363 [00:14<00:16,  3.44it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:11,  4.40it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:06,  7.16it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:03,  9.57it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:02, 12.00it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 16.70it/s]
Loading 0:  95%|█████████▍| 344/363 [00:15<00:00, 20.18it/s]
Loading 0:  96%|█████████▌| 349/363 [00:15<00:00, 23.26it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 29.56it/s]
Loading 0:  99%|█████████▉| 361/363 [00:15<00:00, 32.92it/s]
                                                            
Job chaiml-mistral-nemo-dpo-1800-v1-mkmlizer completed after 115.57s with status: succeeded
Stopping job with name chaiml-mistral-nemo-dpo-1800-v1-mkmlizer
Pipeline stage MKMLizer completed in 116.09s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-mistral-nemo-dpo-1800-v1
Waiting for inference service chaiml-mistral-nemo-dpo-1800-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service chaiml-mistral-nemo-dpo-1800-v1 ready after 241.2031853199005s
Pipeline stage MKMLDeployer completed in 241.73s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.849428653717041s
Received healthy response to inference request in 0.8581724166870117s
Received healthy response to inference request in 1.042309045791626s
Received healthy response to inference request in 1.344191312789917s
Received healthy response to inference request in 0.7255973815917969s
5 requests
0 failed requests
5th percentile: 0.7521123886108398
10th percentile: 0.7786273956298828
20th percentile: 0.8316574096679688
30th percentile: 0.8949997425079346
40th percentile: 0.9686543941497803
50th percentile: 1.042309045791626
60th percentile: 1.1630619525909425
70th percentile: 1.2838148593902587
80th percentile: 1.445238780975342
90th percentile: 1.6473337173461915
95th percentile: 1.748381185531616
99th percentile: 1.829219160079956
mean time: 1.1639397621154786
Pipeline stage StressChecker completed in 7.30s
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 2.52s
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 2.35s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_1800_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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-mistral-nemo-dpo-1800-v1-profiler
Waiting for inference service chaiml-mistral-nemo-dpo-1800-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 2954.25s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_1800_v1 status is now inactive due to auto deactivation removed underperforming models