chaiml-mistral-nemo-dpo-_5482

developer_uid: azuruce

submission_id: chaiml-mistral-nemo-dpo-_5482_v2

model_name: chaiml-mistral-nemo-dpo-_5482_v2

model_group: ChaiML/mistral_nemo_dpo_

status: inactive

timestamp: 2024-12-20T23:18:29+00:00

num_battles: 12735

num_wins: 6058

celo_rating: 1227.73

family_friendly_score: 0.5993999999999999

family_friendly_standard_error: 0.006929929869775018

submission_type: basic

model_repo: ChaiML/mistral_nemo_dpo_round2_albert_20241220_v1-checkpoint-1035

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6300687774027193, 'latency_mean': 1.5870645368099212, 'latency_p50': 1.5837129354476929, 'latency_p90': 1.749022936820984}, {'batch_size': 3, 'throughput': 1.2383203471070356, 'latency_mean': 2.4190783095359802, 'latency_p50': 2.4190014600753784, 'latency_p90': 2.647550106048584}, {'batch_size': 5, 'throughput': 1.5432193797542575, 'latency_mean': 3.224132879972458, 'latency_p50': 3.23342764377594, 'latency_p90': 3.5989881277084352}, {'batch_size': 6, 'throughput': 1.6546325333220475, 'latency_mean': 3.597261766195297, 'latency_p50': 3.5951226949691772, 'latency_p90': 4.078361296653748}, {'batch_size': 8, 'throughput': 1.812282142769708, 'latency_mean': 4.380660601854324, 'latency_p50': 4.352266073226929, 'latency_p90': 5.030973958969116}, {'batch_size': 10, 'throughput': 1.8658706527719766, 'latency_mean': 5.310890859365463, 'latency_p50': 5.3081265687942505, 'latency_p90': 6.113465452194214}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-mistral-nemo-dpo-_5482_v2

is_internal_developer: True

language_model: ChaiML/mistral_nemo_dpo_round2_albert_20241220_v1-checkpoint-1035

model_size: 13B

ranking_group: single

throughput_3p7s: 1.69

us_pacific_date: 2024-12-20

win_ratio: 0.4756968983117393

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-5482-v2-mkmlizer
Waiting for job on chaiml-mistral-nemo-dpo-5482-v2-mkmlizer to finish
chaiml-mistral-nemo-dpo-5482-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-nemo-dpo-5482-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-mistral-nemo-dpo-5482-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-mistral-nemo-dpo-5482-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-mistral-nemo-dpo-5482-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-mistral-nemo-dpo-5482-v2-mkmlizer: ║       /___/                                                         ║
chaiml-mistral-nemo-dpo-5482-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-5482-v2-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-mistral-nemo-dpo-5482-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-mistral-nemo-dpo-5482-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral-nemo-dpo-5482-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-5482-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral-nemo-dpo-5482-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral-nemo-dpo-5482-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-5482-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral-nemo-dpo-5482-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral-nemo-dpo-5482-v2-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-mistral-nemo-dpo-5482-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-5482-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral-nemo-dpo-5482-v2-mkmlizer: Downloaded to shared memory in 40.298s
chaiml-mistral-nemo-dpo-5482-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpcz2c_66w, device:0
chaiml-mistral-nemo-dpo-5482-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral-nemo-dpo-5482-v2-mkmlizer: quantized model in 36.050s
chaiml-mistral-nemo-dpo-5482-v2-mkmlizer: Processed model ChaiML/mistral_nemo_dpo_round2_albert_20241220_v1-checkpoint-1035 in 76.349s
chaiml-mistral-nemo-dpo-5482-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-nemo-dpo-5482-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-nemo-dpo-5482-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-5482-v2
chaiml-mistral-nemo-dpo-5482-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-5482-v2/config.json
chaiml-mistral-nemo-dpo-5482-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-5482-v2/special_tokens_map.json
chaiml-mistral-nemo-dpo-5482-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-5482-v2/tokenizer_config.json
chaiml-mistral-nemo-dpo-5482-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-5482-v2/tokenizer.json
chaiml-mistral-nemo-dpo-5482-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-5482-v2/flywheel_model.0.safetensors
chaiml-mistral-nemo-dpo-5482-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 28.48it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 49.95it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 44.36it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 41.89it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:07, 47.21it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 44.77it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 43.98it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 49.35it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 47.10it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 35.23it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:08, 34.51it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:08, 36.11it/s]
Loading 0:  21%|██        | 75/363 [00:01<00:07, 36.57it/s]
Loading 0:  22%|██▏       | 81/363 [00:01<00:06, 41.81it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:06, 41.56it/s]
Loading 0:  25%|██▌       | 92/363 [00:02<00:06, 41.94it/s]
Loading 0:  27%|██▋       | 99/363 [00:02<00:05, 46.56it/s]
Loading 0:  29%|██▉       | 105/363 [00:02<00:05, 44.52it/s]
Loading 0:  31%|███       | 112/363 [00:02<00:05, 49.35it/s]
Loading 0:  33%|███▎      | 118/363 [00:02<00:05, 42.50it/s]
Loading 0:  35%|███▍      | 126/363 [00:02<00:04, 50.19it/s]
Loading 0:  36%|███▋      | 132/363 [00:03<00:05, 46.05it/s]
Loading 0:  38%|███▊      | 137/363 [00:03<00:05, 43.68it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 34.26it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 35.01it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 33.71it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:05, 40.29it/s]
Loading 0:  45%|████▍     | 163/363 [00:03<00:04, 40.29it/s]
Loading 0:  46%|████▋     | 168/363 [00:04<00:04, 41.23it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:04, 46.69it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:03, 46.10it/s]
Loading 0:  51%|█████     | 186/363 [00:04<00:03, 44.70it/s]
Loading 0:  53%|█████▎    | 192/363 [00:04<00:03, 46.82it/s]
Loading 0:  54%|█████▍    | 197/363 [00:04<00:03, 45.74it/s]
Loading 0:  56%|█████▌    | 202/363 [00:04<00:03, 46.14it/s]
Loading 0:  57%|█████▋    | 208/363 [00:04<00:03, 43.51it/s]
Loading 0:  59%|█████▊    | 213/363 [00:05<00:03, 42.44it/s]
Loading 0:  60%|██████    | 218/363 [00:05<00:03, 43.92it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:04, 33.46it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:03, 34.13it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:04, 32.69it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:03, 39.91it/s]
Loading 0:  67%|██████▋   | 243/363 [00:05<00:02, 41.20it/s]
Loading 0:  68%|██████▊   | 248/363 [00:06<00:03, 33.56it/s]
Loading 0:  70%|███████   | 255/363 [00:06<00:02, 39.22it/s]
Loading 0:  72%|███████▏  | 260/363 [00:06<00:02, 38.32it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 37.87it/s]
Loading 0:  74%|███████▍  | 269/363 [00:06<00:02, 38.15it/s]
Loading 0:  75%|███████▌  | 274/363 [00:06<00:02, 39.74it/s]
Loading 0:  77%|███████▋  | 279/363 [00:06<00:02, 41.74it/s]
Loading 0:  78%|███████▊  | 284/363 [00:06<00:02, 34.92it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 41.94it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 41.38it/s]
Loading 0:  83%|████████▎ | 301/363 [00:07<00:01, 42.91it/s]
Loading 0:  84%|████████▍ | 306/363 [00:14<00:23,  2.45it/s]
Loading 0:  85%|████████▌ | 310/363 [00:14<00:16,  3.19it/s]
Loading 0:  87%|████████▋ | 314/363 [00:14<00:11,  4.19it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:06,  6.28it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:04,  8.72it/s]
Loading 0:  91%|█████████ | 330/363 [00:14<00:03, 10.60it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 16.38it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:00, 19.88it/s]
Loading 0:  96%|█████████▌| 349/363 [00:15<00:00, 22.98it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 29.54it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 32.22it/s]
                                                            
Job chaiml-mistral-nemo-dpo-5482-v2-mkmlizer completed after 104.41s with status: succeeded
Stopping job with name chaiml-mistral-nemo-dpo-5482-v2-mkmlizer
Pipeline stage MKMLizer completed in 104.90s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-mistral-nemo-dpo-5482-v2
Waiting for inference service chaiml-mistral-nemo-dpo-5482-v2 to be ready
Inference service chaiml-mistral-nemo-dpo-5482-v2 ready after 401.40286135673523s
Pipeline stage MKMLDeployer completed in 402.00s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9361968040466309s
Received healthy response to inference request in 1.2636089324951172s
Received healthy response to inference request in 1.3641307353973389s
Received healthy response to inference request in 1.331475019454956s
Received healthy response to inference request in 0.9139492511749268s
5 requests
0 failed requests
5th percentile: 0.9838811874389648
10th percentile: 1.0538131237030028
20th percentile: 1.1936769962310791
30th percentile: 1.277182149887085
40th percentile: 1.3043285846710204
50th percentile: 1.331475019454956
60th percentile: 1.3445373058319092
70th percentile: 1.3575995922088624
80th percentile: 1.4785439491271974
90th percentile: 1.7073703765869142
95th percentile: 1.8217835903167723
99th percentile: 1.9133141613006592
mean time: 1.361872148513794
Pipeline stage StressChecker completed in 8.26s
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 0.69s
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 0.71s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_5482_v2 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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-mistral-nemo-dpo-5482-v2-profiler
Waiting for inference service chaiml-mistral-nemo-dpo-5482-v2-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 2163.95s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_5482_v2 status is now inactive due to auto deactivation removed underperforming models